MMLU Pro benchmark for GGUFs (1 shot)
Collection
"Not all quantized model perform good", serving framework ollama uses NVIDIA gpu, llama.cpp uses CPU with AVX & AMX • 13 items • Updated • 9
Pussy Hut
PussyHut
AI & ML interests
None yet
Recent Activity
liked a model 16 days ago
sokann/Qwen3.5-27B-GGUF-4.165bpw new activity 3 months ago
unsloth/GLM-4.7-Flash-GGUF:NEW: LLama.cpp: Using `ngram-mod` to Get 2x Speed Boost on Long-Chats/Agent! new activity 3 months ago
unsloth/GLM-4.7-Flash-GGUF:High CPU Usage / Slow Context ProcessingOrganizations
None yet
upvoted a collection 9 months ago