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
Patterson
MartinPatterson
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
AesSedai/Qwen3.5-397B-A17B-GGUF:Q4 K_M 489 GB 5-bit size isn't displayed correctly? new activity
1 day ago
AesSedai/Qwen3.5-397B-A17B-GGUF:Dataset Imatrix new activity
6 days ago
XiaomiMiMo/MiMo-V2-Flash:When you're going to release MiMo-V2-Flash(Feb 2026) version? Organizations
None yet
upvoted a collection 4 months ago