CMP 170HX x2

Nvidia · 64 GB VRAM

5recorded runs

186.9best tok/s

5sourced

How it compares — 64 GB per card · multi-GPU

Best verified tok/s per GPU in this VRAM tier — compare any two like-for-like.

Evidence: 5 sourced runs · 2 independent sources · first recorded Sep 4, 2026 · last recorded Sep 23, 2026. What these labels mean.

Model	Quant	Peak VRAM	Headroom
Baichuan-M3-235B	Q3_K_M	118.0 GB	-54.0 GB
Hy3	Q2_K_XL	115.9 GB	-51.9 GB
Hy-MT2-30B-A3B	FP8	115.5 GB	-51.5 GB
Laguna-S-2.1	Q4_K_M	74.6 GB	-10.6 GB

Peak process memory recorded by the submitter on this card — evidence of what fit, not a guarantee. Plan with the VRAM calculator.

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
CMP 170HX x2 · 64 GB	Qwen3.8-Flash-Next	W4A16-FP8PLE	vllm 0.29.0	262052	186.9 ✓	—	—	src
CMP 170HX x2 · 64 GB	Laguna-S-2.1	Q4_K_M	llama.cpp 0.28.0	32768	63.3 ✓	1118.5	74.6	src
CMP 170HX x2 · 64 GB	Hy-MT2-30B-A3B	FP8	vllm 0.28.0	32768	61.4 ✓	1957.4	115.5	src
CMP 170HX x2 · 64 GB	Hy3	Q2_K_XL	llama.cpp 0.28.0	32768	27.6 ✓	250.7	115.9	src
CMP 170HX x2 · 64 GB	Baichuan-M3-235B	Q3_K_M	llama.cpp 0.28.0	32768	26.1 ✓	309.3	118.0	src