Speed test matrix
MiMo-V2.6-Distill-Qwen-9B on H200 NVL 141GB
vllm · 0.30.0 · BF166 contexts (8K–251K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 128K, 251K, 256K
Hardware
- Type
- Discrete GPU
- GPU
- H200 NVL
- VRAM
- 141 GB
- OS
- linux
Engine
- Engine
- vllm
- Version
- 0.30.0
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- cuda-13.2
Run
- Served model
- mimo-v2.6-distill-qwen-9b
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.6.2
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 4,096 tokens
Launch command
"$HOME/env_h200-xiaomimimo-vllm-v0300/bin/vllm" serve XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B --served-model-name mimo-v2.6-distill-qwen-9b --tensor-parallel-size 1 --reasoning-parser mimo --enable-auto-tool-choice --tool-call-parser mimo --max-model-len 262144 --gpu-memory-utilization 0.88 --host 0.0.0.0 --port 8000 --api-key <redacted> --attention-backend FLASH_ATTN
Prefill
prompt tok/s by context length8K context15.9K515 ms TTFT
16K context15.4K1,057 ms TTFT
32K context21K1,538 ms TTFT
64K context25K2,574 ms TTFT
128K context22.8K5,646 ms TTFT
251K context17.5K14,426 ms TTFT
256K context17.9K14,405 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 | 162.066 ms TTFT | Looped | Looped | Looped | Looped | Looped | Looped | Looped |
| 16K | 160.092 ms TTFT | Looped | Looped | Looped | Looped | Looped | Looped | 4,790.41,489 ms TTFT |
| 32K | 156.7120 ms TTFT | Looped | Looped | Looped | Looped | Looped | 2,755.91,180 ms TTFT | Over capacity |
| 64K | Looped | 276.5262 ms TTFT | 495.0223 ms TTFT | Looped | Looped | Looped | Over capacity | Over capacity |
| 128K | Looped | Looped | Looped | Looped | 763.71,632 ms TTFT | Over capacity | Over capacity | Over capacity |
| 251K | Looped | Looped | Looped | Looped | 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 | 15.9K | — | 515 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 15.4K | — | 1,057 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 21K | — | 1,538 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 25K | — | 2,574 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 22.8K | — | 5,646 ms | — | — | 1 | — | — |
| Prefill | 251K | 1 | Valid | 17.5K | — | 14,426 ms | — | — | 1 | — | — |
| Prefill | 256K | 1 | Valid | 17.9K | — | 14,405 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 162.0 | 162.6 | 66 ms | 6.1 ms | 1.0 | 1 | 4,859 | 30.0 s |
| 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 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 128 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 1 | Valid | 160.0 | 160.9 | 92 ms | 6.2 ms | 1.0 | 1 | 4,800 | 30.0 s |
| Sustained decode | 16K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| 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 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 128 | Valid | 4,790.4 | 36.9 | 1,489 ms | 27.1 ms | 128.0 | 0 | 143,872 | 30.0 s |
| Sustained decode | 32K | 1 | Valid | 156.7 | 157.6 | 120 ms | 6.3 ms | 1.0 | 1 | 4,699 | 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 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 64 | Valid | 2,755.9 | 43.2 | 1,180 ms | 23.1 ms | 64.0 | 0 | 82,688 | 30.0 s |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 2 | Valid | 276.5 | 139.8 | 262 ms | 7.2 ms | 2.0 | 2 | 8,296 | 30.0 s |
| Sustained decode | 64K | 4 | Valid | 495.0 | 125.0 | 223 ms | 8.0 ms | 4.0 | 4 | 14,849 | 30.0 s |
| Sustained decode | 64K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 32 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 16 | Valid | 763.7 | 47.5 | 1,632 ms | 21.0 ms | 16.0 | 0 | 22,912 | 30.0 s |
| Sustained decode | 128K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 251K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 251K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 251K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 251K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 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.