llamaperf
Submit

NVIDIA CMP 170HX 64GB (unlocked) vs NVIDIA RTX Pro 6000 Blackwell for local LLMs

10 reports on the NVIDIA CMP 170HX 64GB (unlocked) and 51 on the NVIDIA RTX Pro 6000 Blackwell

Which is faster for local LLMs?

Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 20% higher on the NVIDIA RTX Pro 6000 Blackwell (1,493 GB/s on the NVIDIA CMP 170HX 64GB (unlocked), 1,792 on the NVIDIA RTX Pro 6000 Blackwell). The estimates below compare them on the models people run most.

NVIDIA CMP 170HX 64GB (unlocked)
Memory
64GB
Memory bandwidth
1,493 GB/s
FP16 compute
not on record
Reports
10
NVIDIA RTX Pro 6000 Blackwell
Memory
96GB
Memory bandwidth
1,792 GB/s
FP16 compute
503 TFLOPS
Reports
51

Estimated by the calculator

The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape.

ModelNVIDIA CMP 170HX 64GB (unlocked)NVIDIA RTX Pro 6000 Blackwell
Qwen3.8 27B30.4 t/sQ8_018.3 t/sFP16
Qwen3.8 125B · 6B active127.0 t/sQ3_K_S83.1 t/sQ5_K_S
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settings130.8 t/sQ2_K
Qwen3.6 35B · 3B active109.5 t/sQ8_057.5 t/sFP16
Qwen3.6 27B30.4 t/sQ8_018.3 t/sFP16
Gemma 4 26B · 4B active82.1 t/sQ8_049.3 t/sFP16

Change the context, RAM or model in the calculator: NVIDIA CMP 170HX 64GB (unlocked) · NVIDIA RTX Pro 6000 Blackwell

Every report on each card, with its source: NVIDIA CMP 170HX 64GB (unlocked) · NVIDIA RTX Pro 6000 Blackwell

More comparisons