Speed test matrix
Muse-Glimmer-30B on RTX PRO 6000 Blackwell Server Edition 96GB
vllm · 0.30.1rc1.dev452+g73a583112 · BF165 contexts (8K–123K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 123K, 128K
Hardware
- Type
- Discrete GPU
- GPU
- RTX PRO 6000 Blackwell Server Edition
- VRAM
- 96 GB
- OS
- linux
Engine
- Engine
- vllm
- Version
- 0.30.1rc1.dev452+g73a583112
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- cuda-13.2
- Commit
73a5831127a9
Run
- Served model
- muse-glimmer
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.7.6
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 4,096 tokens
Launch command
env MAX_JOBS=2 FLASHINFER_NVCC_THREADS=1 TORCHINDUCTOR_COMPILE_THREADS=1 "$HOME/env_rtxpro6k-meta-models-vllm-73a5831127a9/bin/vllm" serve meta-models/Muse-Glimmer-30B --served-model-name muse-glimmer --tensor-parallel-size 1 --reasoning-parser muse_glimmer --enable-auto-tool-choice --tool-call-parser muse_glimmer --max-model-len 131072 --gpu-memory-utilization 0.84 --host 0.0.0.0 --port 8000 --api-key <redacted> --generation-config auto --max-num-seqs 64 --attention-backend FLASH_ATTN --speculative-config '{"method":"dflash","model":"meta-models/Muse-Glimmer-30B-assistant","num_speculative_tokens":15}'Prefill
prompt tok/s by context length8K context5,3751,525 ms TTFT
16K context6,3822,535 ms TTFT
32K context6,3305,083 ms TTFT
64K context5,71911,217 ms TTFT
123K context5,16423,840 ms TTFT
128K context5,25924,360 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 8K | Looped | Looped | Looped | Looped | Looped | Looped | Over capacity | Over capacity |
| 16K | Looped | 288.0211 ms TTFT | Looped | Looped | Looped | 759.71,036 ms TTFT | Over capacity | Over capacity |
| 32K | 146.3166 ms TTFT | Looped | Looped | Looped | Looped | Over capacity | Over capacity | Over capacity |
| 64K | 134.9227 ms TTFT | Looped | 332.6358 ms TTFT | 233.2612 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 123K | 130.2357 ms TTFT | Looped | Looped | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Looped: the model kept repeating the same text, so the benchmark discarded this measurement. Over capacity: not run because this many requests at this context would exceed the server's KV cache.
TTFT is measured after the benchmark warms the server's prompt cache, so it mostly excludes prefill.
All measurements
Latencies are medians. Total tok/s is output across all simultaneous requests.| Phase | Context | Requests at once | Status | Total tok/s | Per request tok/s | TTFT | Time between tokens | Average active requests | Completed requests | Output tokens | Measured for |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Prefill | 8K | 1 | Valid | 5,375.0 | — | 1,525 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 6,382.0 | — | 2,535 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 6,330.0 | — | 5,083 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 5,719.0 | — | 11,217 ms | — | — | 1 | — | — |
| Prefill | 123K | 1 | Valid | 5,164.0 | — | 23,840 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 5,259.0 | — | 24,360 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 32 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 2 | Valid | 288.0 | 193.1 | 211 ms | 8.9 ms | 2.0 | 2 | 8,632 | 30.0 s |
| Sustained decode | 16K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 32 | Valid | 759.7 | 25.1 | 1,036 ms | 39.9 ms | 32.0 | 0 | 22,715 | 29.9 s |
| Sustained decode | 16K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Valid | 146.3 | 204.4 | 166 ms | 9.9 ms | 1.0 | 1 | 4,383 | 30.0 s |
| Sustained decode | 32K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 1 | Valid | 134.9 | 160.2 | 227 ms | 8.1 ms | 1.0 | 1 | 4,045 | 30.0 s |
| Sustained decode | 64K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 4 | Valid | 332.6 | 95.9 | 358 ms | 13.4 ms | 4.0 | 2 | 9,959 | 29.9 s |
| Sustained decode | 64K | 8 | Valid | 233.2 | 39.3 | 612 ms | 25.5 ms | 8.0 | 0 | 6,987 | 30.0 s |
| Sustained decode | 64K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 1 | Valid | 130.2 | 269.0 | 357 ms | 3.7 ms | 1.0 | 1 | 3,899 | 29.9 s |
| Sustained decode | 123K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 123K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 123K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Looped: the model kept repeating the same text, so the benchmark discarded this measurement. Over capacity: not run because this many requests at this context would exceed the server's KV cache.