Speed test matrix
Muse-Glimmer-30B-NVFP4 on RTX PRO 6000 Blackwell Server Edition 96GB
vllm · 0.30.1rc1.dev452+g73a583112 · NVFP45 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
- NVFP4
- 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-redhatai-vllm-73a5831127a9d2b8/bin/vllm" serve RedHatAI/Muse-Glimmer-30B-NVFP4 --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 0.86 --host 0.0.0.0 --port 8000 --api-key <redacted> --generation-config auto --speculative-config '{"method":"dflash","model":"meta-models/Muse-Glimmer-30B-assistant","num_speculative_tokens":15}'Prefill
prompt tok/s by context length8K context16.1K507 ms TTFT
16K context16K1,014 ms TTFT
32K context15.8K2,031 ms TTFT
64K context12.6K5,075 ms TTFT
123K context10.1K12,206 ms TTFT
128K context10.4K12,368 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 | 529.2102 ms TTFT | Looped | Looped | Looped | Looped | Looped | 1,435.51,549 ms TTFT |
| 16K | Looped | 538.9111 ms TTFT | Looped | Looped | Looped | Looped | 1,241.21,004 ms TTFT | Over capacity |
| 32K | Looped | Looped | Looped | Looped | Looped | Looped | Over capacity | Over capacity |
| 64K | 171.9173 ms TTFT | Looped | Looped | Looped | Looped | Over capacity | Over capacity | Over capacity |
| 123K | Looped | Looped | Looped | 248.71,075 ms TTFT | Looped | 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 | 16.1K | — | 507 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 16K | — | 1,014 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 15.8K | — | 2,031 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 12.6K | — | 5,075 ms | — | — | 1 | — | — |
| Prefill | 123K | 1 | Valid | 10.1K | — | 12,206 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 10.4K | — | 12,368 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 2 | Valid | 529.2 | 218.1 | 102 ms | 4.6 ms | 2.0 | 4 | 15,880 | 30.0 s |
| 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 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 128 | Valid | 1,435.5 | 12.7 | 1,549 ms | 78.8 ms | 128.0 | 0 | 43,024 | 30.0 s |
| Sustained decode | 16K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 2 | Valid | 538.9 | 299.1 | 111 ms | 3.4 ms | 2.0 | 4 | 16,158 | 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 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 64 | Valid | 1,241.2 | 20.6 | 1,004 ms | 48.5 ms | 64.0 | 0 | 37,235 | 30.0 s |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| 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 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 1 | Valid | 171.9 | 236.3 | 173 ms | 6.2 ms | 1.0 | 1 | 5,153 | 30.0 s |
| Sustained decode | 64K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 123K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 123K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 123K | 8 | Valid | 248.7 | 37.6 | 1,075 ms | 26.6 ms | 8.0 | 0 | 7,454 | 30.0 s |
| Sustained decode | 123K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| 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.