iMatrix-aware MLX-native mixed precision quantizations of Qwen/Qwen-AgentWorld-35B-A3B
🤝 Open to Collab
Matt
Basher17
AI & ML interests
Uploading high-quality MLX quantizations of models I use.
Recent Activity
liked a model 2 days ago
Altworld/Hemmingway-1 liked a model 3 days ago
convaiinnovations/laya new activity 8 days ago
meituan-longcat/LongCat-Flash-Lite-Sparse:mlx-vlm finally added support! Can oMLX merge it?Organizations
models 23
Basher17/Qwen-AgentWorld-35B-A3B-oQ4e
Text Generation • 35B • Updated • 27
Basher17/Qwen-AgentWorld-35B-A3B-oQ6e
Text Generation • 35B • Updated • 21
Basher17/Qwen3.6-35B-A3B-oQ4e-mtp
Image-Text-to-Text • 36B • Updated • 20
Basher17/Qwen3.6-35B-A3B-oQ6e-mtp
Image-Text-to-Text • 36B • Updated • 58 • 1
Basher17/Agents-A1-oQ4e
Text Generation • 35B • Updated • 41 • 1
Basher17/Agents-A1-oQ6e
Text Generation • 35B • Updated • 27 • 1
Basher17/Ornith-1.0-35B-oQ4e
Text Generation • 35B • Updated • 22
Basher17/Ornith-1.0-35B-oQ6e
Text Generation • 35B • Updated • 20
Basher17/Qwen3.6-27B-oQ4e-mtp
Image-Text-to-Text • 28B • Updated • 10
Basher17/Qwen3.6-27B-oQ6e-mtp
Image-Text-to-Text • 28B • Updated • 17
datasets 0
None public yet