olka-fi/Qwen3.5-35B-A3B-MXFP4
Image-Text-to-Text • 20B • Updated • 242 • 1
Oleksandr Kachur
olka-fi
AI & ML interests
None yet
Recent Activity
new activity 4 days ago
olka-fi/MiniMax-M2.5-mxfp4:Model not working/incomplete new activity 5 days ago
olka-fi/Qwen3.5-27B-MXFP4:Why is the file size of 4bit similar to FP8? new activity 10 days ago
olka-fi/Qwen3.5-122B-A10B-MXFP4:Love the quant! Nicely done.Organizations
olka-fi/Qwen3.5-4B-MXFP4
Image-Text-to-Text • 4B • Updated • 162 • 1
olka-fi/Qwen3.5-9B-MXFP4
Image-Text-to-Text • 7B • Updated • 122
olka-fi/Qwen3.5-27B-MXFP4
Image-Text-to-Text • 20B • Updated • 147 • 2
olka-fi/Qwen3.5-122B-A10B-MXFP4
Text Generation • 71B • Updated • 3.43k • 6
olka-fi/MiniMax-M2.5-mxfp4
Text Generation • 123B • Updated • 283 • 1