はじめにリーダーボードDecode calculatorモデルOrganizationsReportsMatrix runsハードウェアベンチマークマーケットプレイスレンタルProAPIドキュメント
言語
Actual Computer — Every computer, one endpoint

Matrix runs

A matrix run measures prompt reading (prefill) and generation (decode) speed in one go, across several context lengths and numbers of simultaneous requests. Run one with lmx speed-test matrix run.

Clear

Matching runs 351

Submitted by @Sandberg. Newest first. Page 5 of 15.
  • Qwen3-14B-FP8RTX 3090 24GB · vllm 0.32.0 · FP83 contexts × 8 concurrency levels
    Peak decode
    202.8 tok/s
    Peak prefill
    3,018 tok/s
  • Ministral-3-3B-Instruct-2512-FP8RTX 3060 12GB · vllm 0.32.0 · FP86 contexts × 8 concurrency levels
    Peak decode
    696.2 tok/s
    Peak prefill
    1,828 tok/s
  • Fara1.5-27B-AWQ-W4A16RTX 3090 24GB · vllm 0.32.0 · AWQ W4A164 contexts × 8 concurrency levels
    Peak decode
    332.3 tok/s
    Peak prefill
    2,144 tok/s
  • Cosmos-Reason2-8BRTX 3090 24GB · vllm 0.32.0 · BF165 contexts × 8 concurrency levels
    Peak decode
    644.4 tok/s
    Peak prefill
    3,932 tok/s
  • Qwen3.5-4B-FP8-dynamicRTX 3060 12GB · vllm 0.32.0 · FP8 dynamic6 contexts × 8 concurrency levels
    Peak decode
    545.9 tok/s
    Peak prefill
    2,186 tok/s
  • Llama-3.2-3B-InstructRTX 3090 24GB · vllm 0.32.0 · BF165 contexts × 8 concurrency levels
    Peak decode
    1,232.0 tok/s
    Peak prefill
    14.7K tok/s
  • Nemotron-Cascade-2-30B-A3B-AWQ-4bitRTX 3090 24GB · vllm 0.32.0 · AWQ 4-bit6 contexts × 8 concurrency levels
    Peak decode
    1,075.9 tok/s
    Peak prefill
    8,169 tok/s
  • Qwen3-0.6BRTX 3090 24GB · vllm 0.32.0 · BF163 contexts × 8 concurrency levels
    Peak decode
    1,756.7 tok/s
    Peak prefill
    39.4K tok/s
  • Qwen3-1.7BRTX 3090 24GB · vllm 0.32.0 · BF163 contexts × 8 concurrency levels
    Peak decode
    1,509.4 tok/s
    Peak prefill
    23.8K tok/s
  • Qwen3.5-4B-FP8-dynamicRTX 3060 12GB · vllm 0.32.0 · FP8 dynamic6 contexts × 8 concurrency levels
    Peak decode
    909.3 tok/s
    Peak prefill
    2,370 tok/s
  • Ministral-3-3B-Instruct-2512RTX 3090 24GB · vllm 0.32.0 · BF166 contexts × 8 concurrency levels
    Peak decode
    2,983.4 tok/s
    Peak prefill
    12.5K tok/s
  • Fara1.5-4BRTX 3090 24GB · vllm 0.32.0 · BF166 contexts × 8 concurrency levels
    Peak decode
    1,834.8 tok/s
    Peak prefill
    11.8K tok/s
  • Qwen3.5-27B-AWQ-4bitRTX 3090 24GB · vllm 0.32.0 · AWQ 4-bit4 contexts × 8 concurrency levels
    Peak decode
    173.3 tok/s
    Peak prefill
    1,555 tok/s
  • Qwen3-Next-80B-A3B-Instruct-FP8CMP 170HX 64GB ×2 · vllm 0.32.0rc1.dev249+g18305948a · FP86 contexts × 8 concurrency levels
    Peak decode
    2,821.5 tok/s
    Peak prefill
    10.8K tok/s
  • Agents-A1-4B-FP8RTX 3060 12GB · vllm 0.32.0 · FP86 contexts × 8 concurrency levels
    Peak decode
    890.6 tok/s
    Peak prefill
    2,341 tok/s
  • Agents-A1-4BRTX 3090 24GB · vllm 0.32.0 · BF166 contexts × 8 concurrency levels
    Peak decode
    1,811.6 tok/s
    Peak prefill
    11.9K tok/s
  • NVIDIA-Nemotron-3-Nano-4B-BF16RTX 3090 24GB · vllm 0.32.0 · BF166 contexts × 8 concurrency levels
    Peak decode
    2,579.8 tok/s
    Peak prefill
    14K tok/s
  • Fara1.5-4B-FP8RTX 3060 12GB · vllm 0.32.0 · FP86 contexts × 8 concurrency levels
    Peak decode
    909.6 tok/s
    Peak prefill
    2,375 tok/s
  • Qwen3-8BRTX 3090 24GB · vllm 0.32.0 · BF163 contexts × 8 concurrency levels
    Peak decode
    396.4 tok/s
    Peak prefill
    7,042 tok/s
  • Llama-3.3-70B-Instruct-FP8-dynamicCMP 170HX 64GB ×2 · vllm 0.32.0rc1.dev249+g18305948a · FP8 dynamic5 contexts × 8 concurrency levels
    Peak decode
    234.7 tok/s
    Peak prefill
    1,356 tok/s
  • granite-4.2-30b-nvfp4RTX 3090 24GB · vllm 0.32.0 · NVFP44 contexts × 8 concurrency levels
    Peak decode
    278.4 tok/s
    Peak prefill
    1,173 tok/s
  • DeepSeek-R1-Distill-Qwen-14B-FP8-dynamicRTX 3090 24GB · vllm 0.32.0 · FP8 dynamic5 contexts × 8 concurrency levels
    Peak decode
    338.4 tok/s
    Peak prefill
    2,137 tok/s
  • NVIDIA-Nemotron-3-Nano-4B-FP8RTX 3060 12GB · vllm 0.32.0 · FP86 contexts × 8 concurrency levels
    Peak decode
    952.3 tok/s
    Peak prefill
    3,010 tok/s
  • gpt-oss-120bCMP 170HX 64GB ×2 · vllm 0.32.0rc1.dev249+g18305948a · MXFP45 contexts × 8 concurrency levels
    Peak decode
    2,009.9 tok/s
    Peak prefill
    7,548 tok/s
  • Hy-MT2-7B-FP8RTX 3090 24GB · vllm 0.32.0 · FP85 contexts × 8 concurrency levels
    Peak decode
    239.1 tok/s
    Peak prefill
    6,574 tok/s