"Not all quantized model perform good", serving framework ollama uses NVIDIA gpu, llama.cpp uses CPU with AVX & AMX
v1k
xbruce22
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
facebook/deit-tiny-patch16-224 new activity 6 days ago
deepseek-ai/dspark_qwen3_4b_block7:why block 7 updated a model 19 days ago
xbruce22/gemma-4-e2b-reasoning-lora