llama.cpp on the NVIDIA CMP 170HX 64GB (unlocked)
On the NVIDIA CMP 170HX 64GB (unlocked), llama.cpp runs Qwen3.6 27B at 4-bit at a median 38.0 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 | llama.cpp | Other engines |
|---|---|---|
| Qwen3.6 27B 4-bit | 38.0 t/sone report, context not stated | no other engine reported |
3 llama.cpp 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.
- Qwen3.6 27B · Q4_K_M38.0 t/s
- Qwen3.6 35B · 3B active · Q6_K63.0 t/s(speculative decoding)
- DeepSeek V4 Flash 284B · 13B active · Q4_K_XL29.0 t/s(4 cards)
Frequently asked
How fast is llama.cpp on the NVIDIA CMP 170HX 64GB (unlocked)?
On the NVIDIA CMP 170HX 64GB (unlocked), llama.cpp runs Qwen3.6 27B at 4-bit at a median 38.0 tokens per second for generation, from 1 plain run (context not stated).