vLLM on the NVIDIA CMP 170HX 64GB (unlocked)
On the NVIDIA CMP 170HX 64GB (unlocked), vLLM runs Qwen3-Next 80B · 3B active at 4-bit at a median 116.0 tokens per second for generation, from 1 plain run (context not stated).
Speed by model on the NVIDIA CMP 170HX 64GB (unlocked)
Plain runs only: one device, one request, no speculative decoding, the whole model in memory. Each row is one model size at one bit class, with the other engines' plain runs of the same model on this card beside it. Context length and build still differ between runs, and each side shows its own.
| Model | vLLM | Other engines |
|---|---|---|
| Qwen3-Next 80B · 3B active 4-bit | 116.0 t/sone report, context not stated | no other engine reported |
7 vLLM reports on the NVIDIA CMP 170HX 64GB (unlocked)
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- DeepSeek V4.1 Flash 552B · 16B active117.0 t/s(8 cards, speculative decoding, part in system RAM)
- Qwen3.8 125B · 6B active · W4A16101.3 t/s(2 cards, speculative decoding, part in system RAM)
- DeepSeek V4 Flash · FP895.0 t/s(4 cards, speculative decoding, 2 requests at once)
- Qwen3-Next 80B · 3B active · W4A16116.0 t/s
- DeepSeek V4 Flash 284B · 13B active · MXFP4+FP898.1 t/s(4 cards, speculative decoding)
- Qwen3.8 27B · W4A16147.0 t/s(speculative decoding)
- Qwen3.8 27B · FP8PP 3468.0 t/s
Frequently asked
How fast is vLLM on the NVIDIA CMP 170HX 64GB (unlocked)?
On the NVIDIA CMP 170HX 64GB (unlocked), vLLM runs Qwen3-Next 80B · 3B active at 4-bit at a median 116.0 tokens per second for generation, from 1 plain run (context not stated).