Speed test matrix
Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit on CMP 170HX 64GB
vllm · 0.32.0rc1.dev249+g18305948a · AWQ 4-bit6 contexts (0–248K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 128K
Hardware
- Type
- Discrete GPU
- GPU
- CMP 170HX
- VRAM
- 64 GB
- CPU
- 2x Intel Xeon E5-2630 v3
- RAM
- 64 GB
- OS
- Ubuntu 26.04.1
Engine
- Engine
- vllm
- Version
- 0.32.0rc1.dev249+g18305948a
- Quantization
- AWQ 4-bit
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- ghcr.io/morrowmake/vllm-cmp170hx@sha256:5b45c4d6feafefe2eba962375b0a9a0b64fd22b9e05abb4d1966f14a32a2db79
Run
- Served model
- bench
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.8.0
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 8,192 tokens
Launch command
# Untuned out-of-the-box baseline. Spec decode: none # 1x NVIDIA CMP 170HX 64GB (cmpunlocker), 180 W limit, PCIe Gen2 x4 | 2x Intel Xeon E5-2630 v3 | 64 GB DDR4 | Ubuntu 26.04.1, NVIDIA driver 610.57.04 | vLLM: Morrowmake vllm-cmp170hx image vllm serve cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit --max-model-len 262144 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code
Prefill
prompt tok/s by context length8K context7,9571,031 ms TTFT
16K context6,8402,375 ms TTFT
32K context5,0106,454 ms TTFT
64K context3,18620,258 ms TTFT
128K context1,83970,088 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 0 | 151.673 ms TTFT | 265.694 ms TTFT | 455.1106 ms TTFT | 744.7134 ms TTFT | 1,183.9194 ms TTFT | 1,819.0327 ms TTFT | Over capacity | Over capacity |
| 16K | Looped | Looped | Looped | Looped | Looped | Over capacity | Over capacity | Over capacity |
| 32K | 110.5269 ms TTFT | 168.2345 ms TTFT | Looped | 291.5861 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 84.9446 ms TTFT | 118.5627 ms TTFT | 150.7944 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 128K | 58.5953 ms TTFT | 71.91,238 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 248K | 35.9Requests queued1,480 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Requests queued: the server could not run all requests at once, so some waited in a queue. 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 | 7,957.0 | — | 1,031 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 6,840.0 | — | 2,375 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 5,010.0 | — | 6,454 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 3,186.0 | — | 20,258 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 1,839.0 | — | 70,088 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 151.6 | 152.7 | 73 ms | 6.5 ms | 1.0 | 0 | 4,548 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 265.6 | 134.3 | 94 ms | 7.4 ms | 2.0 | 0 | 7,966 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 455.1 | 115.7 | 106 ms | 8.6 ms | 4.0 | 0 | 13,656 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 744.7 | 95.7 | 134 ms | 10.5 ms | 8.0 | 0 | 22,352 | 30.0 s |
| Sustained decode | 0 | 16 | Valid | 1,183.9 | 76.7 | 194 ms | 13.0 ms | 16.0 | 0 | 35,520 | 30.0 s |
| Sustained decode | 0 | 32 | Valid | 1,819.0 | 59.3 | 327 ms | 16.9 ms | 32.0 | 0 | 54,560 | 30.0 s |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| 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 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Valid | 110.5 | 111.0 | 269 ms | 9.0 ms | 1.0 | 0 | 3,315 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 168.2 | 84.5 | 345 ms | 11.8 ms | 2.0 | 0 | 5,044 | 30.0 s |
| Sustained decode | 32K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 8 | Valid | 291.5 | 36.4 | 861 ms | 27.5 ms | 8.0 | 0 | 8,744 | 30.0 s |
| Sustained decode | 32K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 1 | Valid | 84.9 | 85.2 | 446 ms | 11.7 ms | 1.0 | 0 | 2,545 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 118.5 | 59.5 | 627 ms | 16.8 ms | 2.0 | 0 | 3,554 | 30.0 s |
| Sustained decode | 64K | 4 | Valid | 150.7 | 37.7 | 944 ms | 26.5 ms | 4.0 | 0 | 4,520 | 30.0 s |
| Sustained decode | 64K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 128K | 1 | Valid | 58.5 | 58.7 | 953 ms | 17.0 ms | 1.0 | 0 | 1,754 | 30.0 s |
| Sustained decode | 128K | 2 | Valid | 71.9 | 36.1 | 1,238 ms | 27.7 ms | 2.0 | 0 | 2,156 | 30.0 s |
| Sustained decode | 128K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 1 | Requests queued | 35.9 | 37.0 | 1,480 ms | 27.0 ms | 1.0 | 0 | 1,075 | 30.0 s |
| Sustained decode | 248K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Requests queued: the server could not run all requests at once, so some waited in a queue. 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.