GPQA-verified mixed-precision MLX quants of Qwen3.6 for Apple Silicon — ThinkingCap 4.6bpw beats the official Q4_K_M at smaller size.
ALISVOLATPROPRIIS
avlp12
AI & ML interests
MLX quantization, Apple Silicon inference, MoE models, local LLM deployment, medical AI, geopolitical early warning systems, humanoid robotics, semiconductor/memory markets, multi-agent systems
Recent Activity
updated a collection 5 days ago
Qwen3.6 — Alis MLX Dynamic updated a collection 5 days ago
Qwen3.6 — Alis MLX Dynamic updated a collection 5 days ago
Qwen3.6 — Alis MLX DynamicOrganizations
None yet
models 22
avlp12/Qwen3.6-35B-A3B-Alis-MLX-Dynamic
Image-Text-to-Text • 36B • Updated • 448 • 1
avlp12/ThinkingCap-Qwen3.6-27B-Alis-MLX-Dynamic
Image-Text-to-Text • 28B • Updated • 855 • 2
avlp12/Qwen3.6-27B-Alis-MLX-Dynamic
Image-Text-to-Text • 28B • Updated • 293
avlp12/MiniMax-M3-Alis-MLX-Dynamic
Image-Text-to-Text • 427B • Updated • 731
avlp12/Hy3-Alis-MLX-Dynamic
Text Generation • 295B • Updated • 3.15k • 8
avlp12/lance-pt-snapshot
Updated
avlp12/Lance-3B-Alis-MLX-Traced
Any-to-Any • Updated • 1
avlp12/CyberRealistic-Z-Image-Turbo-v4-mflux-4bit
Text-to-Image • Updated • 204
avlp12/CyberRealistic-Z-Image-Turbo-v4-mflux-8bit
Text-to-Image • Updated • 187
avlp12/Krea-2-Turbo-Alis-MLX-mixed-4-8
Text-to-Image • Updated • 195
datasets 0
None public yet