Model

Qwenimage-text-to-text222 uji kecepatan

Qwen3.6-35B-A3B

Qwen / Qwen3.6-35B-A3B

MoE3B active / 35B totalqwen3_5_moeconversational

Terbaik6.0k tok/s

Median74.8 tok/s

Min6.4 tok/s

Eval score· 2 evalsBF16+

91.6%

Qwenimage-text-to-text193 uji kecepatan

Qwen3.6-27B

Qwen / Qwen3.6-27B

27Bqwen3_5conversational

Terbaik1.4k tok/s

Median44.6 tok/s

Min1.6 tok/s

Qwentext-generation13 uji kecepatan

Ornith-1.5-35B-A3B

ornith-ai / Ornith-1.5-35B-A3B

MoE3B active / 35B totalqwen3_5_moeimage-text-to-textconversational

Terbaik3.7k tok/s

Median193 tok/s

Min35.4 tok/s

gemma-4-26B-A4B

google / gemma-4-26B-A4B

MoE4B active / 26B totalgemma4

Qwen3.5-9B-Base

Qwen / Qwen3.5-9B-Base

9Bqwen3_5conversational

Qwenimage-text-to-text236 uji kecepatan

Qwen3.8-27B-MTP-GGUF

Jackrong / Qwen3.8-27B-MTP-GGUF

27Bllama.cppvisionmultimodal

Terbaik72.6 tok/s

Median36.6 tok/s

Min11.6 tok/s

Qwenimage-text-to-text36 uji kecepatan

Qwen3.8-Flash-Next

Qwen / Qwen3.8-Flash-Next

180Bqwen4_expconversational

Terbaik205 tok/s

Median66.3 tok/s

Min7.7 tok/s

Eval score· 2 evalsW4B+

85.7%

text-generation20 uji kecepatan

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

nvidia / NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

MoE3B active / 30B totalnemotron_hnvidianemotron-3.5

Terbaik7.2k tok/s

Median195 tok/s

Min49.8 tok/s

image-text-to-text61 uji kecepatan

GLM-5.3-Flash

zai-org / GLM-5.3-Flash

321Bglm5_nextconversationalen

Terbaik1.5k tok/s

Median79.9 tok/s

Min15.3 tok/s

Eval score· 8 evalsNVFP4+

73.4%

text-generation129 uji kecepatan

Ornith-1.5-35B-A3B-GGUF

ornith-ai / Ornith-1.5-35B-A3B-GGUF

MoE3B active / 35B totalconversational

Terbaik131 tok/s

Median105 tok/s

Min26.5 tok/s

Gemmaany-to-any1 uji kecepatan

gemma-4-12B

google / gemma-4-12B

12Bgemma4_unifiedimage-text-to-text

Terbaik25.8 tok/s

Median25.8 tok/s

Min25.8 tok/s

Minimaxtext-generation40 uji kecepatan

MiniMax-M2.7

MiniMaxAI / MiniMax-M2.7

Terbaik496 tok/s

Median32.2 tok/s

Min0.5 tok/s

Deepseektext-generation73 uji kecepatan

DeepSeek-V4-Flash-0731

deepseek-ai / DeepSeek-V4-Flash-0731

MoE304Bdeepseek_v48-bitfp8

Terbaik404 tok/s

Median84.8 tok/s

Min19.0 tok/s

Eval score· 5 evalsFP8

90.4%

Gemmaany-to-any3 uji kecepatan

gemma-4-E4B

google / gemma-4-E4B

4Bgemma4image-text-to-text

Terbaik71.2 tok/s

Median70.5 tok/s

Min70.5 tok/s

granite-4.1-30b-base

ibm-granite / granite-4.1-30b-base

30Bgranitelanguagegranite-4.1

Qwen3.5-35B-A3B-Base

Qwen / Qwen3.5-35B-A3B-Base

MoE3B active / 35B totalqwen3_5_moeconversational

Qwentext-generation14 uji kecepatan

Ornith-1.0-35B

ornith-ai / Ornith-1.0-35B

MoE35Bqwen3_5_moeimage-text-to-textconversational

Terbaik164 tok/s

Median71.8 tok/s

Min54.1 tok/s

NVIDIA-Nemotron-Nano-12B-v2-Base

nvidia / NVIDIA-Nemotron-Nano-12B-v2-Base

12Bnvidiaenes

Qwentext-generation106 uji kecepatan

Ornith-1.5-9B

ornith-ai / Ornith-1.5-9B

9Bqwen3_5image-text-to-textconversational

Terbaik3.8k tok/s

Median75.3 tok/s

Min9.2 tok/s

Eval score· 1 evalBF16

81.7%

Qwen3-8B-Base

Qwen / Qwen3-8B-Base

8Bqwen3conversational

Qwenimage-text-to-text19 uji kecepatan

Qwen3.5-27B

Qwen / Qwen3.5-27B

27Bqwen3_5conversational

Terbaik287 tok/s

Median25.1 tok/s

Min2.2 tok/s

GLM-5.2

zai-org / GLM-5.2

MoE753Bglm_moe_dsaconversationalen

gemma-4-31B

google / gemma-4-31B

31Bgemma4

Deepseektext-generation38 uji kecepatan

DeepSeek-V4-Flash

deepseek-ai / DeepSeek-V4-Flash

MoE291Bdeepseek_v48-bitfp8

Terbaik262 tok/s

Median28.5 tok/s

Min7.0 tok/s

Eval score· 1 evalIQ3_XXS

94.8%

text-generation47 uji kecepatan

Laguna-S-2.1

poolside / Laguna-S-2.1

MoE118Blagunalaguna-s-2.1vllm

Terbaik127 tok/s

Median41.9 tok/s

Min15.1 tok/s

LFM2.5-8B-A1B-Base

LiquidAI / LFM2.5-8B-A1B-Base

MoE1B active / 8B totallfm2_moeliquidlfm2.5

Gpttext-generation67 uji kecepatan

gpt-oss-20b

openai / gpt-oss-20b

MoE20Bgpt_ossvllmconversational

Terbaik5.1k tok/s

Median149 tok/s

Min12.0 tok/s

Qwentext-generation2 uji kecepatan

Qwen2.5-7B

Qwen / Qwen2.5-7B

7Bqwen2conversationalen

Terbaik1.4k tok/s

Median1.4k tok/s

Min1.4k tok/s

0.3Bintern_vit_6bfeature-extraction

InternViT-300M-448px

OpenGVLab / InternViT-300M-448px

image-feature-extraction

image-text-to-text35 uji kecepatan

Muse-Glimmer-30B

meta-models / Muse-Glimmer-30B

30Bmuse_glimmerconversational

Terbaik1.5k tok/s

Median43.7 tok/s

Min12.8 tok/s

Qwen3-0.6B-Base

Qwen / Qwen3-0.6B-Base

0.6Bqwen3conversational

Phitext-generation10 uji kecepatan

Phi-4-mini-reasoning

microsoft / Phi-4-mini-reasoning

Llamatext-generation50 uji kecepatan

Llama-3.2-3B-Instruct

meta-llama / Llama-3.2-3B-Instruct

3Bfacebookmetallama-3

Terbaik489 tok/s

Median75.9 tok/s

Min10.0 tok/s

text-generation54 uji kecepatan

Ornith-1.5-9B-GGUF

ornith-ai / Ornith-1.5-9B-GGUF

text-generation39 uji kecepatan

LFM2-350M

LiquidAI / LFM2-350M

Qwentext-generation29 uji kecepatan

Qwen3-Coder-30B-A3B-Instruct

Qwen / Qwen3-Coder-30B-A3B-Instruct

Terbaik136 tok/s

Median80.5 tok/s

Min14.4 tok/s

Eval score· 1 evalQ4_K_M

92.1%

Qwentext-generation44 uji kecepatan

Ornith-1.0-9B

ornith-ai / Ornith-1.0-9B

9Bqwen3_5image-text-to-textconversational

Terbaik77.5 tok/s

Median25.7 tok/s

Min3.8 tok/s

Eval score· 3 evalsQ4_K_M

56.0%

Qwen3-14B-Base

Qwen / Qwen3-14B-Base

14Bqwen3conversational

text-generation6 uji kecepatan

Laguna-XS-2.1

poolside / Laguna-XS-2.1

MoE33Blagunalaguna-xs-2.1vllm

Terbaik296 tok/s

Median106 tok/s

Min72.5 tok/s

LFM2.5-1.2B-Base

LiquidAI / LFM2.5-1.2B-Base

1.2Blfm2liquidlfm2.5

gemma-3-12b-pt

google / gemma-3-12b-pt

12Bgemma3

2Bgemma4image-text-to-text

gemma-4-E2B

google / gemma-4-E2B

Gemmaany-to-any

Llamatext-generation40 uji kecepatan

MiniCPM5-1B-GGUF

openbmb / MiniCPM5-1B-GGUF

1Bminicpmminicpm5long-context

Qwen3.5-4B-Base

Qwen / Qwen3.5-4B-Base

4Bqwen3_5conversational

Deepseek-R1text-generation28 uji kecepatan

DeepSeek-R1-Distill-Qwen-7B

deepseek-ai / DeepSeek-R1-Distill-Qwen-7B

7Bqwen2conversational

Terbaik144 tok/s

Median63.6 tok/s

Min12.8 tok/s

Ornstein3.6-27B-MTP-NSC-ACE-SABER

GestaltLabs / Ornstein3.6-27B-MTP-NSC-ACE-SABER

27Bqwen3_5qwen3.6mtp

Qwentext-generation28 uji kecepatan

AceReason-Nemotron-1.1-7B

nvidia / AceReason-Nemotron-1.1-7B

7Bqwen2nvidiareasoning

Terbaik79.8 tok/s

Median63.6 tok/s

Min12.8 tok/s

text-generation24 uji kecepatan

LFM2-8B-A1B

LiquidAI / LFM2-8B-A1B

MoE1B active / 8B totallfm2_moeliquidlfm2

Terbaik243 tok/s

Median211 tok/s

Min9.9 tok/s

Phitext-generation3 uji kecepatan

phi-4

microsoft / phi-4

Qwentext-generation9 uji kecepatan

Nex-N2-mini

nex-agi / Nex-N2-mini

MoE35Bqwen3_5_moeimage-text-to-textconversational

Terbaik107 tok/s

Median104 tok/s

Min40.5 tok/s

Mistral-Small-24B-Base-2501

mistralai / Mistral-Small-24B-Base-2501

24Bvllmmistral-commonen

Qwenimage-text-to-text15 uji kecepatan

Qwen3.5-122B-A10B

Qwen / Qwen3.5-122B-A10B

MoE10B active / 122B totalqwen3_5_moeconversational

Terbaik50.1 tok/s

Median26.4 tok/s

Min3.2 tok/s

Deepseek-R1text-generation10 uji kecepatan

DeepSeek-R1-Distill-Qwen-14B

deepseek-ai / DeepSeek-R1-Distill-Qwen-14B

14Bqwen2conversational

Terbaik50.9 tok/s

Median38.0 tok/s

Min9.0 tok/s

text-generation33 uji kecepatan

Ornith-1.0-9B-GGUF

ornith-ai / Ornith-1.0-9B-GGUF

LFM2.5-350M-Base

LiquidAI / LFM2.5-350M-Base

350Mlfm2liquidlfm2.5

GLM-4.7-Flash

zai-org / GLM-4.7-Flash

MoE31Bglm4_moe_liteconversationalen

Terbaik212 tok/s

Median93.3 tok/s

Min17.2 tok/s

Qwen3-1.7B-Base

Qwen / Qwen3-1.7B-Base

1.7Bqwen3conversational

text-generation16 uji kecepatan

Nemotron-Cascade-2-30B-A3B

nvidia / Nemotron-Cascade-2-30B-A3B

MoE3B active / 30B totalnemotron_hnvidianemotron-cascade-2

Terbaik197 tok/s

Median155 tok/s

Min89.8 tok/s

Ministral-3-3B-Base-2512

mistralai / Ministral-3-3B-Base-2512

3Bvllmmistral3mistral-common

Gpttext-generation29 uji kecepatan

gpt-oss-120b

openai / gpt-oss-120b

MoE120Bgpt_ossvllmconversational

Terbaik2.8k tok/s

Median115 tok/s

Min34.4 tok/s

Eval score· 2 evalsMXFP4

78.4%

Llamatext-generation31 uji kecepatan

Meta-Llama-3-8B-Instruct

meta-llama / Meta-Llama-3-8B-Instruct

8Bfacebookmetallama-3

Terbaik148 tok/s

Median48.4 tok/s

Min13.6 tok/s

text-generation31 uji kecepatan

Ornith-1.0-35B-GGUF

ornith-ai / Ornith-1.0-35B-GGUF

Qwen2.5-3B

Qwen / Qwen2.5-3B

3Bqwen2conversationalen

Qwentext-generation12 uji kecepatan

Agents-A1

InternScience / Agents-A1

MoE35Bqwen3_5_moeimage-text-to-textmoe

Qwenimage-text-to-text1 uji kecepatan

Qwen3.5-0.8B-Base

Qwen / Qwen3.5-0.8B-Base

0.8Bqwen3_5conversational

Terbaik2.7k tok/s

Median2.7k tok/s

Min2.7k tok/s

LFM2.5-230M-Base

LiquidAI / LFM2.5-230M-Base

230Mlfm2liquidlfm2.5

MoE3B active / 30B totalconversational

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF

lmstudio-community / NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF

26 uji kecepatan

Terbaik203 tok/s

Median36.4 tok/s

Min14.4 tok/s

Trinity-Mini-Base-Pre-Anneal

arcee-ai / Trinity-Mini-Base-Pre-Anneal

Arceetext-generation

MoE26Bafmoeenes

Qwen3-4B-Base

Qwen / Qwen3-4B-Base

4Bqwen3conversational

reka-flash-3

RekaAI / reka-flash-3

Llama23 uji kecepatan

Qwen2.5-14B

Qwen / Qwen2.5-14B

14Bqwen2conversationalen

Qwentext-generation19 uji kecepatan

Qwen3-Coder-Next

Qwen / Qwen3-Coder-Next

MoE80Bqwen3_nextconversational

Terbaik80.8 tok/s

Median55.8 tok/s

Min47.0 tok/s

GLM-5.3-Flash-BF16

zai-org / GLM-5.3-Flash-BF16

321Bglm5_nextconversationalen

Qwen2.5-32B

Qwen / Qwen2.5-32B

32Bqwen2conversationalen

BTL-4

badtheorylabs / BTL-4

MoE35Bqwen3_5_moeimage-text-to-textagentic

translation7 uji kecepatan

Hy-MT2-7B

tencent / Hy-MT2-7B

7Bhunyuan_v1_densetext-generationzh

Deepseek-R1text-generation4 uji kecepatan

DeepSeek-R1-Distill-Qwen-32B

deepseek-ai / DeepSeek-R1-Distill-Qwen-32B

32Bqwen2conversational

Terbaik23.3 tok/s

Median22.3 tok/s

Min21.4 tok/s

GLM-5.3

zai-org / GLM-5.3

MoE753Bglm_moe_dsaconversationalen

Qwentext-generation18 uji kecepatan

Nemotron-Cascade-14B-Thinking

nvidia / Nemotron-Cascade-14B-Thinking

14Bqwen3nvidianemotron-cascade

Terbaik51.9 tok/s

Median34.2 tok/s

Min6.2 tok/s

text-generation17 uji kecepatan

GLM-Z1-32B-0414

zai-org / GLM-Z1-32B-0414

32Bglm4conversationalzh

Terbaik22.5 tok/s

Median16.4 tok/s

Min5.7 tok/s

Olmo-3-1125-32B

allenai / Olmo-3-1125-32B

32Bolmo3en

Mellum2-12B-A2.5B-Instruct

JetBrains / Mellum2-12B-A2.5B-Instruct

MoE2.5B active / 12B totalmellumconversationalen

Terbaik83.5 tok/s

Median51.8 tok/s

Min41.8 tok/s

Llamatext-generation16 uji kecepatan

MiniCPM5-1B

openbmb / MiniCPM5-1B

1Bminicpmminicpm5long-context

Coheretext-generation17 uji kecepatan

North-Mini-Code-1.0

CohereLabs / North-Mini-Code-1.0

MoE30Bcohere2_moeconversationalchat

Terbaik258 tok/s

Median102 tok/s

Min38.7 tok/s

Deepseekimage-text-to-text14 uji kecepatan

DeepSeek-V4.1-Flash

deepseek-ai / DeepSeek-V4.1-Flash

763Bdeepseek_v41text-generationconversational

Terbaik352 tok/s

Median74.0 tok/s

Min31.7 tok/s

Llama-3.1-8B

meta-llama / Llama-3.1-8B

8Bfacebookmetallama-3

Opttext-generation16 uji kecepatan

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

nvidia / NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

MoE3B active / 30B totalnemotron_hnvidianemotron-3.5

Terbaik6.7k tok/s

Median254 tok/s

Min77.1 tok/s

Eval score· 3 evalsNVFP4

74.8%

image-text-to-text5 uji kecepatan

Step-3.7-Flash

stepfun-ai / Step-3.7-Flash

MoE201Bstep3p7vision-languagemultimodal

Terbaik31.0 tok/s

Median30.8 tok/s

Min30.7 tok/s

gemma-3-1b-pt

google / gemma-3-1b-pt

Gemmatext-generation

1Bgemma3_text

Agents-A1-4B

InternScience / Agents-A1-4B

4Bqwen3_5image-text-to-textvlm

QUEST-30B-RL

osunlp / QUEST-30B-RL

MoE30Bqwen3_moequestconversational

any-to-any5 uji kecepatan

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

nvidia / Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

MoE3B active / 30B totalNemotronH_Nano_Omni_Reasoning_V3feature-extractionnvidia

6Bintern_vit_6bfeature-extraction

InternViT-6B-224px

OpenGVLab / InternViT-6B-224px

image-feature-extraction

Qwen3-30B-A3B-Base

Qwen / Qwen3-30B-A3B-Base

Qwentext-generation4 uji kecepatan

KAT-Coder-V2.5-Dev

Kwaipilot / KAT-Coder-V2.5-Dev

MoE35Bqwen3_5_moeimage-text-to-textcode

Terbaik75.9 tok/s

Median75.0 tok/s

Min66.3 tok/s

Mistral-Medium-3.5-128B

mistralai / Mistral-Medium-3.5-128B

Mistral13 uji kecepatan

MoE3B active / 35B totalqwen3_5_moe

Tess-4-35B-A3B

migtissera / Tess-4-35B-A3B

Qwen12 uji kecepatan

Terbaik155 tok/s

Median140 tok/s

Min33.1 tok/s

GLM-4.5-Air

zai-org / GLM-4.5-Air

MoE110Bglm4_moeconversationalen

Terbaik2.5k tok/s

Median103 tok/s

Min6.2 tok/s

text-generation12 uji kecepatan

granite-4.0-h-micro

ibm-granite / granite-4.0-h-micro

MoE3Bgranitemoehybridlanguagegranite-4.0

Terbaik141 tok/s

Median41.9 tok/s

Min7.9 tok/s

Eval score· 3 evalsQ4_K_M

53.3%

SmolLM2-135M

HuggingFaceTB / SmolLM2-135M

135Men

Ling-3.0-tiny

inclusionAI / Ling-3.0-tiny

MoE8Bbailing_hybridconversational

Terbaik369 tok/s

Median129 tok/s

Min52.6 tok/s

text-generation11 uji kecepatan

GLM-Z1-Rumination-32B-0414

zai-org / GLM-Z1-Rumination-32B-0414

32Bglm4conversationalzh

Terbaik22.4 tok/s

Median19.7 tok/s

Min8.8 tok/s

Minimaxtext-generation2 uji kecepatan

MiniMax-M2.5

MiniMaxAI / MiniMax-M2.5

Terbaik504 tok/s

Median419 tok/s

Min334 tok/s

SmolLM2-360M

HuggingFaceTB / SmolLM2-360M

360Men

Mistral-Small-3.1-24B-Base-2503

mistralai / Mistral-Small-3.1-24B-Base-2503

24Bvllmmistral3mistral-common

Seed-OSS-36B-Instruct

ByteDance-Seed / Seed-OSS-36B-Instruct

36Bseed_ossvllmconversational

Qwentext-generation10 uji kecepatan

Qwen3.6-27B-DFlash

z-lab / Qwen3.6-27B-DFlash

27Bqwen3feature-extractiondflash

Terbaik215 tok/s

Median39.2 tok/s

Min26.9 tok/s

Qwen3.5-2B-Base

Qwen / Qwen3.5-2B-Base

2Bqwen3_5conversational

Spark-X2.5-4B-Base

XHToken / Spark-X2.5-4B-Base

4Bspark2_5llmsparkx2_5

LFM2.5-2.6B-Base

LiquidAI / LFM2.5-2.6B-Base

2.6Blfm2liquidlfm2.5

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

nvidia / NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

MoE3B active / 30B totalnemotron_hnvidiaconversational

Terbaik313 tok/s

Median286 tok/s

Min117 tok/s

Ling-3.0-flash

inclusionAI / Ling-3.0-flash

MoE127Bbailing_hybridconversational

Terbaik72.3 tok/s

Median43.4 tok/s

Min33.6 tok/s

translation9 uji kecepatan

Hunyuan-MT-7B

tencent / Hunyuan-MT-7B

7Bhunyuan_v1_densetext-generation

Terbaik98.1 tok/s

Median74.3 tok/s

Min28.5 tok/s

text-generation5 uji kecepatan

MiMo-V2.5

XiaomiMiMo / MiMo-V2.5

MoE311Bmimo_v2multimodalvision-language

Terbaik33.9 tok/s

Median32.7 tok/s

Min28.1 tok/s

Qwen2.5-0.5B

Qwen / Qwen2.5-0.5B

0.5Bqwen2conversationalen

MoE3B active / 30B totalhy_v3text-generationzh

Hy-MT2-30B-A3B

tencent / Hy-MT2-30B-A3B

translation

Llamatext-generation7 uji kecepatan

Llama-3.2-1B-Instruct

meta-llama / Llama-3.2-1B-Instruct

1Bfacebookmetallama-3

Terbaik448 tok/s

Median184 tok/s

Min68.2 tok/s

8Binternlm3conversational

internlm3-8b-instruct

internlm / internlm3-8b-instruct

Internlmtext-generation

Nemotron-Cascade-8B

nvidia / Nemotron-Cascade-8B

8Bqwen3nvidiaNemotron-Cascade

UI-TARS-7B-DPO

ByteDance-Seed / UI-TARS-7B-DPO

7Bqwen2_vlmultimodalgui

text-generation8 uji kecepatan

EXAONE-3.5-7.8B-Instruct

LGAI-EXAONE / EXAONE-3.5-7.8B-Instruct

7.8Bexaonelg-aiexaone-3.5

Terbaik26.8 tok/s

Median25.7 tok/s

Min11.2 tok/s

text-generation8 uji kecepatan

Ling-2.6-flash

inclusionAI / Ling-2.6-flash

MoE107Bbailing_hybridconversationalen

Terbaik94.9 tok/s

Median86.2 tok/s

Min82.3 tok/s

Qwen2.5-72B

Qwen / Qwen2.5-72B

72Bqwen2conversationalen

Gpttext-generation5 uji kecepatan

Tinystories-gpt-0.1-3m

segestic / Tinystories-gpt-0.1-3m

Qwentext-generation4 uji kecepatan

Qwen3-30B-A3B-Instruct-2507

Qwen / Qwen3-30B-A3B-Instruct-2507

Terbaik100 tok/s

Median72.5 tok/s

Min16.6 tok/s

text-generation7 uji kecepatan

Kimi-Linear-48B-A3B-Instruct

moonshotai / Kimi-Linear-48B-A3B-Instruct

MoE3B active / 48B totalkimi_linearconversational

Terbaik281 tok/s

Median233 tok/s

Min90.0 tok/s

rwkv-7-world

BlinkDL / rwkv-7-world

Starcodertext-generation

rwkvcausal-lmen

Llama-3.1-70B

meta-llama / Llama-3.1-70B

70Bfacebookmetallama-3

NVIDIA-Nemotron-3-Super-120B-A12B-BF16

nvidia / NVIDIA-Nemotron-3-Super-120B-A12B-BF16

MoE12B active / 120B totalnemotron_hnvidianemotron-3

Hy3

tencent / Hy3

MoE299Bhy_v3hunyuanhy3

Deepseek-Codertext-generation6 uji kecepatan

DeepSeek-Coder-V2-Lite-Instruct

deepseek-ai / DeepSeek-Coder-V2-Lite-Instruct

MoE16Bdeepseek_v2conversational

Terbaik150 tok/s

Median87.0 tok/s

Min39.0 tok/s

Llamatext-generation4 uji kecepatan

MiniCPM5-2B

openbmb / MiniCPM5-2B

2Bminicpmminicpm5long-context

Terbaik118 tok/s

Median66.8 tok/s

Min61.6 tok/s

glm-4-9b-chat

zai-org / glm-4-9b-chat

Chatglm

9Bglmthudmzh

Qwentext-generation5 uji kecepatan

Qwen3-Coder-Next-FP8

Qwen / Qwen3-Coder-Next-FP8

MoE80Bqwen3_nextconversationalfp8

Terbaik190 tok/s

Median152 tok/s

Min112 tok/s

Llamatext-generation5 uji kecepatan

Llama-2-7b-hf

meta-llama / Llama-2-7b-hf

7Bfacebookmetallama-2

Terbaik202 tok/s

Median50.4 tok/s

Min19.1 tok/s

Qwenimage-text-to-text3 uji kecepatan

Qwen3-VL-8B-Instruct

Qwen / Qwen3-VL-8B-Instruct

8Bqwen3_vlconversational

Terbaik95.9 tok/s

Median89.8 tok/s

Min58.8 tok/s

Qwen2.5-1.5B

Qwen / Qwen2.5-1.5B

1.5Bqwen2conversationalen

Qwentext-generation5 uji kecepatan

Qwen3-32B

Qwen / Qwen3-32B

32Bqwen3conversational

Terbaik79.3 tok/s

Median22.8 tok/s

Min3.2 tok/s

Opttext-generation5 uji kecepatan

NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

nvidia / NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

MoE12B active / 120B totalnemotron_hnvidianemotron-3

Terbaik262 tok/s

Median175 tok/s

Min49.6 tok/s

Qwen3-235B-A22B

Qwen / Qwen3-235B-A22B

MoE22B active / 235B totalqwen3_moeconversational

Spark-X2.5-1.7B-Base

XHToken / Spark-X2.5-1.7B-Base

1.7Bspark2_5llmsparkx2_5

Qwentext-generation4 uji kecepatan

Qwen3-235B-A22B-Thinking-2507

Qwen / Qwen3-235B-A22B-Thinking-2507

MoE22B active / 235B totalqwen3_moeconversational

Terbaik17.5 tok/s

Median15.8 tok/s

Min13.0 tok/s

granite-4.1-8b-base

ibm-granite / granite-4.1-8b-base

8Bgranitelanguagegranite-4.1

Qwen2.5-VL-7B-Instruct

Qwen / Qwen2.5-VL-7B-Instruct

7Bqwen2_5_vlmultimodalconversational

NVIDIA-Nemotron-3-Nano-4B-FP8

nvidia / NVIDIA-Nemotron-3-Nano-4B-FP8

4Bnemotron_hnvidiaconversational

Deepseektext-generation4 uji kecepatan

DeepSeek-V4-Flash-DSpark

deepseek-ai / DeepSeek-V4-Flash-DSpark

MoE165Bdeepseek_v48-bitfp8

Terbaik262 tok/s

Median213 tok/s

Min46.4 tok/s

gemma-3-4b-pt

google / gemma-3-4b-pt

4Bgemma3

gemma-3n-E4B

google / gemma-3n-E4B

4Bgemma3nautomatic-speech-recognitionautomatic-speech-translation

Minimaxtext-generation2 uji kecepatan

MiniMax-M2

MiniMaxAI / MiniMax-M2

Terbaik493 tok/s

Median398 tok/s

Min303 tok/s

GLM-5.1

zai-org / GLM-5.1

MoE754Bglm_moe_dsaconversationalen

text-generation4 uji kecepatan

granite-4.1-30b

ibm-granite / granite-4.1-30b

30Bgranitelanguagegranite-4.1

Terbaik17.9 tok/s

Median16.4 tok/s

Min15.6 tok/s

Gemmatext-generation4 uji kecepatan

Gemopus-4-26B-A4B-it

Jackrong / Gemopus-4-26B-A4B-it

MoE4B active / 26B totalgemma4instruction-tunedreasoning

Terbaik64.3 tok/s

Median55.0 tok/s

Min45.7 tok/s

Llamatext-generation3 uji kecepatan

MiniCPM5-2B-GGUF

openbmb / MiniCPM5-2B-GGUF

2Bminicpmminicpm5long-context

Terbaik60.5 tok/s

Median39.1 tok/s

Min33.7 tok/s

MiMo-V2.6-Flash-RL

XiaomiMiMo / MiMo-V2.6-Flash-RL

MoE311Bmimo_v2multimodalvision-language

Terbaik193 tok/s

Median189 tok/s

Min154 tok/s

gemma-3-27b-pt

google / gemma-3-27b-pt

27Bgemma3

Nex-N2.5-mini

nex-agi / Nex-N2.5-mini

MoE35Bqwen3_5_moeimage-text-to-textconversational

Qwentext-generation3 uji kecepatan

Qwen3-Coder-30B-A3B-Instruct-FP8

Qwen / Qwen3-Coder-30B-A3B-Instruct-FP8

MoE3B active / 30B totalqwen3_moeconversationalfp8

Terbaik81.9 tok/s

Median48.9 tok/s

Min26.1 tok/s

Qwenimage-text-to-text2 uji kecepatan

Qwen3-VL-30B-A3B-Instruct

Qwen / Qwen3-VL-30B-A3B-Instruct

MoE3B active / 30B totalqwen3_vl_moeconversational

Terbaik56.6 tok/s

Median52.2 tok/s

Min47.7 tok/s

Falcon-H1-0.5B-Base

tiiuae / Falcon-H1-0.5B-Base

Falcontext-generation

0.5Bfalcon_h1en

Gemmatext-generation3 uji kecepatan

functiongemma-270m-it

google / functiongemma-270m-it

270Mgemma3_textgemma3google

Terbaik206 tok/s

Median193 tok/s

Min169 tok/s

Falcontext-generation3 uji kecepatan

Falcon-H1-Tiny-90M-Instruct

tiiuae / Falcon-H1-Tiny-90M-Instruct

90Mfalcon_h1edgeconversational

Terbaik495 tok/s

Median425 tok/s

Min338 tok/s

270Mgemma3_textgemma3google

gemma-3-270m

google / gemma-3-270m

Gemmatext-generation

EXAONE-3.5-7.8B-Instruct-GGUF

LGAI-EXAONE / EXAONE-3.5-7.8B-Instruct-GGUF

7.8Blg-aiexaoneexaone-3.5

Ornith-1.0-397B

ornith-ai / Ornith-1.0-397B

MoE397Bqwen3_5_moeimage-text-to-textconversational

Mellum2-12B-A2.5B-Thinking

JetBrains / Mellum2-12B-A2.5B-Thinking

MoE2.5B active / 12B totalmellumconversationalen

Gemmaimage-text-to-text1 uji kecepatan

diffusiongemma-26B-A4B-it

google / diffusiongemma-26B-A4B-it

MoE4B active / 26B totaldiffusion_gemmaconversational

Terbaik529 tok/s

Median529 tok/s

Min529 tok/s

MiniCPM3-4B

openbmb / MiniCPM3-4B

4Bminicpm3conversationalzh

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

nvidia / NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

MoE12B active / 120B totalnemotron_h_omninvidianemotron-3.5

SmolLM2-1.7B

HuggingFaceTB / SmolLM2-1.7B

1.7Ben

Qwen3-4B-Thinking-2507

Qwen / Qwen3-4B-Thinking-2507

4Bqwen3conversational

TinyLlama-1.1B-Chat-v1.0

TinyLlama / TinyLlama-1.1B-Chat-v1.0

Ternary-Bonsai-8B-unpacked

prism-ml / Ternary-Bonsai-8B-unpacked

8Bqwen3prismmlbonsai

MoE17B active / 109B totalllama4facebookmeta

Llama-4-Scout-17B-16E

meta-llama / Llama-4-Scout-17B-16E

Llamaimage-text-to-text

Deepseekimage-text-to-text1 uji kecepatan

DeepSeek-V4-Flash-Vision-Exp

deepseek-ai / DeepSeek-V4-Flash-Vision-Exp

MoE305Bdeepseek_v4text-generation8-bit

Terbaik180 tok/s

Median180 tok/s

Min180 tok/s

Qwenimage-text-to-text2 uji kecepatan

Qwen3.8-27B-Uncensored-int4-AutoRound

johannrplaster / Qwen3.8-27B-Uncensored-int4-AutoRound

27Bqwen3_5vllmintel-xpu

Terbaik136 tok/s

Median117 tok/s

Min97.8 tok/s

stories-llama2-50k

delphi-suite / stories-llama2-50k

LFM2-24B-A2B

LiquidAI / LFM2-24B-A2B

MoE2B active / 24B totallfm2_moeliquidlfm2

Terbaik161 tok/s

Median161 tok/s

Min161 tok/s

models-moved

ggml-org / models-moved

Qwentext-generation2 uji kecepatan

Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED

jcbtc / Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED

Eval score· 1 evalROCmFP4

90.5%

text-generation2 uji kecepatan

MobileLLM-350M

facebook / MobileLLM-350M

350Mmobilellmfacebookmeta

Terbaik981 tok/s

Median714 tok/s

Min448 tok/s

text-generation2 uji kecepatan

MobileLLM-125M

facebook / MobileLLM-125M

125Mmobilellmfacebookmeta

Terbaik1.3k tok/s

Median987 tok/s

Min703 tok/s

OLMo-2-0425-1B

allenai / OLMo-2-0425-1B

1Bolmo2en

text-generation2 uji kecepatan

LFM2-700M

LiquidAI / LFM2-700M

Llamatext-generation2 uji kecepatan

h2o-danube3-500m-chat

h2oai / h2o-danube3-500m-chat

0.5Bgptllmlarge language model

Terbaik163 tok/s

Median134 tok/s

Min105 tok/s

granite-4.0-1b-base

ibm-granite / granite-4.0-1b-base

MoE1Bgranitemoehybridlanguagegranite-4.0

Phi-4-mini-instruct

microsoft / Phi-4-mini-instruct

Phitext-generation

4Bphi3nlpcode

image-text-to-text1 uji kecepatan

Kimi-K2.5

moonshotai / Kimi-K2.5

1Tkimi_k25feature-extractioncompressed-tensors

Terbaik74.0 tok/s

Median74.0 tok/s

Min74.0 tok/s

Minimaxtext-generation2 uji kecepatan

MiniMax-M2.1

MiniMaxAI / MiniMax-M2.1

Terbaik499 tok/s

Median416 tok/s

Min333 tok/s

Qwenimage-text-to-text2 uji kecepatan

Qwen3.5-35B-A3B-4bit

mlx-community / Qwen3.5-35B-A3B-4bit

MoE3B active / 35B totalqwen3_5_moemlxconversational

Terbaik140 tok/s

Median122 tok/s

Min105 tok/s

Optimage-text-to-text1 uji kecepatan

Comet_60B_A12B_NVFP4

MultiverseComputingCAI / Comet_60B_A12B_NVFP4

60Bnemotron_h_omniconversationalen

Terbaik18.2 tok/s

Median18.2 tok/s

Min18.2 tok/s

granite-4.0-350m-base

ibm-granite / granite-4.0-350m-base

MoE350Mgranitemoehybridlanguagegranite-4.0

LaMini-GPT-774M

MBZUAI / LaMini-GPT-774M

Gpttext-generation

774Mgpt2en

granite-docling-258M

ibm-granite / granite-docling-258M

258Midefics3text-generationdocuments

bge-base-en-v1.5-gguf

CompendiumLabs / bge-base-en-v1.5-gguf

Qwentext-to-speech1 uji kecepatan

VieNeu-TTS-0.3B

pnnbao-ump / VieNeu-TTS-0.3B

TIPO-100M

KBlueLeaf / TIPO-100M

SmolLM2-135M-GGUF

QuantFactory / SmolLM2-135M-GGUF

harrier-oss-v1-0.6b

calculatortamer / harrier-oss-v1-0.6b

0.6Bsentence-transformersqwen3mteb

Phitext-to-speech1 uji kecepatan

VieNeu-TTS-v2-Turbo-GGUF

pnnbao-ump / VieNeu-TTS-v2-Turbo-GGUF

ttsvietnamesebilingual

Terbaik1.2k tok/s

Median1.2k tok/s

Min1.2k tok/s

test-gguf

rarad / test-gguf

TinyStories-656K

raincandy-u / TinyStories-656K

llama2tinyllamasvalidation

tiny1m

shibatch / tiny1m

Llama1 uji kecepatan

Terbaik5.0k tok/s

Median5.0k tok/s

Min5.0k tok/s

SmolLM-135M

HuggingFaceTB / SmolLM-135M

135Men

MiniLM-L12-H384-uncased

microsoft / MiniLM-L12-H384-uncased

text-classification

bert

30Msentence-transformersbertsentence-similarity

bge-small-en-v1.5

BAAI / bge-small-en-v1.5

feature-extraction

SmolLM2-360M-GGUF

QuantFactory / SmolLM2-360M-GGUF

1Bultravoxfeature-extractionar

ultravox-v0_5-llama-3_2-1b

fixie-ai / ultravox-v0_5-llama-3_2-1b

Llamaaudio-text-to-text

Qwentext-generation1 uji kecepatan

Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

Jackrong / Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

2Bqwen3_5unslothqwen3.5-2B

Terbaik341 tok/s

Median341 tok/s

Min341 tok/s

Qwen2-0.5B

Qwen / Qwen2-0.5B

0.5Bqwen2pretrainedconversational

Hare-1.1B-base-0.5v-GGUF

mradermacher / Hare-1.1B-base-0.5v-GGUF

MiniCPM5-2B-LocalAI

weareapexcreators / MiniCPM5-2B-LocalAI

LFM2.5-230M-LocalAI

weareapexcreators / LFM2.5-230M-LocalAI

Qwen3.5-4B-MTP-LocalAI

weareapexcreators / Qwen3.5-4B-MTP-LocalAI

4Bimatrixconversational

Terbaik187 tok/s

Median187 tok/s

Min187 tok/s

0.6Bpii_maskingpiiprivacy

PII-Tracer

perplexity-ai / PII-Tracer

Qwentoken-classification

Granite-4.1-3B-LocalAI

weareapexcreators / Granite-4.1-3B-LocalAI

1 uji kecepatan

3Bimatrixconversational

Terbaik230 tok/s

Median230 tok/s

Min230 tok/s

Qwen3.5-2B-MTP-LocalAI

weareapexcreators / Qwen3.5-2B-MTP-LocalAI

2Bimatrixconversational

Terbaik343 tok/s

Median343 tok/s

Min343 tok/s

Ornith-1.0-9B-MTP-LocalAI

weareapexcreators / Ornith-1.0-9B-MTP-LocalAI

LFM2.5-350M-LocalAI

weareapexcreators / LFM2.5-350M-LocalAI

Qwen3.5-0.8B-LocalAI

weareapexcreators / Qwen3.5-0.8B-LocalAI

0.8Bimatrixconversational

Terbaik466 tok/s

Median466 tok/s

Min466 tok/s

LFM2.5-1.2B-Instruct-LocalAI

weareapexcreators / LFM2.5-1.2B-Instruct-LocalAI

Gemma4-12B-Uncensored-LocalAI

weareapexcreators / Gemma4-12B-Uncensored-LocalAI

Qwen3.5-4B-Uncensored-LocalAI

weareapexcreators / Qwen3.5-4B-Uncensored-LocalAI

TinyMistral-248M-v2

Locutusque / TinyMistral-248M-v2

Mistraltext-generation

248Men

Qwentext-to-speech1 uji kecepatan

VieNeu-TTS-v2

pnnbao-ump / VieNeu-TTS-v2

290Mqwen3podcastcode-switching

Terbaik790 tok/s

Median790 tok/s

Min790 tok/s

TinyLlama-1.1B-Chat-v0.3

TinyLlama / TinyLlama-1.1B-Chat-v0.3

1.1Ben

sentence-similarity1 uji kecepatan

sentence-bert-swedish-cased

KBLab / sentence-bert-swedish-cased

120Msentence-transformersbertfeature-extraction

Terbaik876 tok/s

Median876 tok/s

Min876 tok/s

Bonsai-27B-unpacked

prism-ml / Bonsai-27B-unpacked

27Bqwen3_5conversationalprismml

Bonsai-1.7B-unpacked

prism-ml / Bonsai-1.7B-unpacked

1.7Bqwen3prismmlbonsai

feature-extraction1 uji kecepatan

bge-small-en-v1.5-GGUF

unsloth / bge-small-en-v1.5-GGUF

sentence-transformerssentence-similaritymteb

Terbaik618 tok/s

Median618 tok/s

Min618 tok/s

Kolibri-1-BF16

Aleph-Alpha / Kolibri-1-BF16

MoE78Bvllmkolibri1reasoning

Ling-3.0-tiny-GGUF

inclusionAI / Ling-3.0-tiny-GGUF

qwen-3.8-27b-abliterated

heterodoxin / qwen-3.8-27b-abliterated

Ternary-Bonsai-1.7B-unpacked

prism-ml / Ternary-Bonsai-1.7B-unpacked

1.7Bqwen3prismmlbonsai

Ternary-Bonsai-2-27B-DFlash2-vllm

fraserprice / Ternary-Bonsai-2-27B-DFlash2-vllm

GLM-5.3-BF16

zai-org / GLM-5.3-BF16

MoE753Bglm_moe_dsaconversationalen

Terbaik6843.6k tok/s

Median6843.6k tok/s

Min6843.6k tok/s

Ling-3.0-flash-int4

inclusionAI / Ling-3.0-flash-int4

MoE127Bbailing_hybridconversationalcompressed-tensors

Terbaik37.3 tok/s

Median37.3 tok/s

Min37.3 tok/s

Falcon3-7B-Base

tiiuae / Falcon3-7B-Base

7Bfalcon3enfr

Qwentext-generation1 uji kecepatan

Ornith-1.5-35B-A3B-NVFP4

ornith-ai / Ornith-1.5-35B-A3B-NVFP4

MoE3B active / 35B totalqwen3_5_moeimage-text-to-textconversational

Terbaik259 tok/s

Median259 tok/s

Min259 tok/s

Eval score· 3 evalsNVFP4

70.9%

Qwen3-30B-A3B-Thinking-2507

Qwen / Qwen3-30B-A3B-Thinking-2507

bitnet-b1.58-2B-4T-bf16

microsoft / bitnet-b1.58-2B-4T-bf16

2Bbitnetchatlarge-language-model

Ministral-3-14B-Base-2512

mistralai / Ministral-3-14B-Base-2512

14Bvllmmistral3mistral-common

rnj-1-instruct-GGUF

EssentialAI / rnj-1-instruct-GGUF

GLM-4.6V-Flash

zai-org / GLM-4.6V-Flash

10Bglm4vconversationalzh

gemma-3n-E4B-it-text-GGUF

lmstudio-community / gemma-3n-E4B-it-text-GGUF

Deepseek-R1text-generation

DeepSeek-R1-0528-Qwen3-8B

deepseek-ai / DeepSeek-R1-0528-Qwen3-8B

8Bqwen3conversational

Deepseek-Codertext-generation1 uji kecepatan

DeepSeek-Coder-V2-Lite-Instruct-FP8

RedHatAI / DeepSeek-Coder-V2-Lite-Instruct-FP8

MoE16Bdeepseek_v2fp8vllm

Terbaik237 tok/s

Median237 tok/s

Min237 tok/s

Qwen3-Next-80B-A3B-Instruct

Qwen / Qwen3-Next-80B-A3B-Instruct

MoE3B active / 80B totalqwen3_nextconversational

Kimi-K3

moonshotai / Kimi-K3

2.8Tkimi_k3feature-extractioncompressed-tensors

Inkling-Small

thinkingmachines / Inkling-Small

MoE266Binkling_mm_modelconversationalaudio-text-to-text

Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

HauhauCS / Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

4Buncensoredqwen3.5en

Terbaik82.9 tok/s

Median82.9 tok/s

Min82.9 tok/s

Harmonic-Hermes-9B-GGUF

DJLougen / Harmonic-Hermes-9B-GGUF

9Bhermesqwen3_5reasoning

Terbaik39.2 tok/s

Median39.2 tok/s

Min39.2 tok/s

Qwen3.5-27B-Uncensored-HauhauCS-Aggressive

HauhauCS / Qwen3.5-27B-Uncensored-HauhauCS-Aggressive

Eval score· 5 evalsQ4_K_M

27Buncensoredqwen3.5en

Terbaik30.8 tok/s

Median30.8 tok/s

Min30.8 tok/s

91.5%

Mistral-Nemo-Base-2407

mistralai / Mistral-Nemo-Base-2407

12Bvllmmistral-commonen

Falcontext-generation1 uji kecepatan

Falcon-H1-Tiny-Tool-Calling-90M

tiiuae / Falcon-H1-Tiny-Tool-Calling-90M

90Mfalcon_h1edgeconversational

Terbaik434 tok/s

Median434 tok/s

Min434 tok/s

Falcontext-generation1 uji kecepatan

Falcon-H1-Tiny-Coder-90M

tiiuae / Falcon-H1-Tiny-Coder-90M

Gpttext-generation1 uji kecepatan

TinyStories-33M

roneneldan / TinyStories-33M

tinystories-lay4-hs128-hd2-1M

ivnle / tinystories-lay4-hs128-hd2-1M

qwen-3-14b-instruct-gguf

lm-kit / qwen-3-14b-instruct-gguf

12Bgemma-4gemmablereasoning

Gemmable-4-12B-MTP-GGUF

Mia-AiLab / Gemmable-4-12B-MTP-GGUF

Gemma1 uji kecepatan

Terbaik71.2 tok/s

Median71.2 tok/s

Min71.2 tok/s

Deepseek-Codertext-generation1 uji kecepatan

DeepSeek-Coder-V2-Lite-Instruct-GGUF

bartowski / DeepSeek-Coder-V2-Lite-Instruct-GGUF

imatrixconversational

Terbaik57.1 tok/s

Median57.1 tok/s

Min57.1 tok/s

Gemmaimage-text-to-text1 uji kecepatan

gemma-4-31B-v2-MLX-4bit

jdfelo / gemma-4-31B-v2-MLX-4bit

Minimaximage-text-to-text

MiniMax-M3

MiniMaxAI / MiniMax-M3

MoE427Bminimax_m3_vlmultimodalmoe

image-text-to-text1 uji kecepatan

Unlimited-OCR

baidu / Unlimited-OCR

MoE3Bunlimited-ocrfeature-extractionbaidu

Terbaik365 tok/s

Median365 tok/s

Min365 tok/s

Gemmaimage-text-to-text1 uji kecepatan

gemma-4-26B-A4B-it-QAT-MLX-4bit

lmstudio-community / gemma-4-26B-A4B-it-QAT-MLX-4bit

MoE4B active / 26B totalgemma4mlxconversational

Terbaik65.3 tok/s

Median65.3 tok/s

Min65.3 tok/s

granite-4.1-8b

ibm-granite / granite-4.1-8b

8Bgranitelanguagegranite-4.1

Optimage-text-to-text1 uji kecepatan

Step-3.7-Flash-NVFP4

stepfun-ai / Step-3.7-Flash-NVFP4

MoE104Bstep3p7vision-languagemultimodal

Terbaik27.4 tok/s

Median27.4 tok/s

Min27.4 tok/s

Qwable-3.6-35b

Mia-AiLab / Qwable-3.6-35b

20Buncensoredabliteratedmxfp4

GPT-OSS-20B-Uncensored-HauhauCS-Aggressive

HauhauCS / GPT-OSS-20B-Uncensored-HauhauCS-Aggressive

Gpt1 uji kecepatan

Terbaik66.8 tok/s

Median66.8 tok/s

Min66.8 tok/s

Deepseek-R11 uji kecepatan

UncensoredLM-DeepSeek-R1-Distill-Qwen-14B

uncensoredai / UncensoredLM-DeepSeek-R1-Distill-Qwen-14B

Qwen3.5-9B-Red_Team

LuisPPB16 / Qwen3.5-9B-Red_Team

9Bqwen3_5llama.cppunsloth

Terbaik35.9 tok/s

Median35.9 tok/s

Min35.9 tok/s

Qwen3.5-0.8B-Q8_0.gguf

Manojb / Qwen3.5-0.8B-Q8_0.gguf

Qwentext-generation1 uji kecepatan

Qwen3.6-35B-A3B-4bit-DWQ

mlx-community / Qwen3.6-35B-A3B-4bit-DWQ

MoE3B active / 35B totalmlxqwen3_5_moeconversational

Terbaik78.9 tok/s

Median78.9 tok/s

Min78.9 tok/s

Qwenimage-text-to-text1 uji kecepatan

Qwen3.5-122B-A10B-GPTQ-Int4

Qwen / Qwen3.5-122B-A10B-GPTQ-Int4

MoE10B active / 122B totalqwen3_5_moeconversational4-bit

Terbaik49.1 tok/s

Median49.1 tok/s

Min49.1 tok/s

Llama-2-7b

meta-llama / Llama-2-7b

7Bfacebookmetallama-2

Terbaik110 tok/s

Median110 tok/s

Min110 tok/s

GLM-5

zai-org / GLM-5

MoE754Bglm_moe_dsaconversationalen

Deepseektext-generation1 uji kecepatan

DeepSeek-V4-Flash-2bit-DQ

mlx-community / DeepSeek-V4-Flash-2bit-DQ

MoE284Bmlxdeepseek_v4conversational

Terbaik17.0 tok/s

Median17.0 tok/s

Min17.0 tok/s

Qwenimage-text-to-text1 uji kecepatan

Qwen3-VL-2B-Instruct

Qwen / Qwen3-VL-2B-Instruct

2Bqwen3_vlconversational

Terbaik27.9 tok/s

Median27.9 tok/s

Min27.9 tok/s

Llamaimage-text-to-text1 uji kecepatan

Gemopus-4-26B-A4B-it-GGUF

Jackrong / Gemopus-4-26B-A4B-it-GGUF

MoE4B active / 26B totalgemma4llama.cppvision

Terbaik94.5 tok/s

Median94.5 tok/s

Min94.5 tok/s

LFM2.5-24B-A2B-Base

LiquidAI / LFM2.5-24B-A2B-Base

MoE2B active / 24B totallfm2_moeliquidlfm2.5

Kimi-K2.6

moonshotai / Kimi-K2.6

1Tkimi_k25feature-extractioncompressed-tensors

MiMo-V2.6-Flash-MOPD

XiaomiMiMo / MiMo-V2.6-Flash-MOPD

MoE311Bmimo_v2multimodalvision-language

Devstral-2-123B-Instruct-2512

mistralai / Devstral-2-123B-Instruct-2512

123Bvllmministral3mistral-common

Kimi-K2.7-Code

moonshotai / Kimi-K2.7-Code

1Tkimi_k25feature-extractioncompressed-tensors

Qwen2-VL-7B

Qwen / Qwen2-VL-7B

7Bqwen2_vlmultimodalconversational

Qwen3.5-9B-NSC-ACE-SABER-GGUF

GestaltLabs / Qwen3.5-9B-NSC-ACE-SABER-GGUF

9Bqwen3_5nsc-acesaber

MoE2B active / 24B totalconversational

LFM2-24B-A2B-GGUF

lmstudio-community / LFM2-24B-A2B-GGUF