llamaperf

CMP 170HX vs RTX 3060 12GB

For running local LLMs · 27 reports across 6 models

Side A
CMP 170HX
Vendor
nvidia
VRAM
8GB
Memory
Discrete
Side B
RTX 3060 12GB
Vendor
nvidia
VRAM
12GB
Memory
Discrete

Highest reported generation speed by model family

These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →

ModelCMP 170HXRTX 3060 12GB
Qwen3.8up to 2400Bn=150.6n=12
Qwen3.6up to 35B210.0n=270.0n=5
DeepSeek V4 Flashup to 285B29.0n=110.1n=2
Gemma 4up to 31B60.0n=2
KAT-Coder V2.5-Dev14.2n=1
Qwen3.5up to 122B12.0n=1

More comparisons