Qwen3.8-27B for Apple silicon — vision tower (333 tensors, bf16) and vendor MTP head both preserved and verified. 8-bit / 6-bit / 4-bit AWQ.
ALISVOLATPROPRIIS PRO
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
new activity 2 days ago
avlp12/Motif-3-Alis-MLX-8bit:Any feedback? updated a model 4 days ago
avlp12/Qwen3.8-27B-Alis-MLX-4bit updated a model 4 days ago
avlp12/Qwen3.8-27B-Alis-MLX-6bitOrganizations
None yet
models 36
avlp12/Qwen3.8-27B-Alis-MLX-8bit
Image-Text-to-Text • 8B • Updated • 1.07k • 5
avlp12/Qwen3.8-27B-Alis-MLX-6bit
Image-Text-to-Text • 6B • Updated • 493
avlp12/Qwen3.8-27B-Alis-MLX-4bit
Image-Text-to-Text • 5B • Updated • 970 • 2
avlp12/Kimi-K3-Alis-MLX-Dynamic-2.10bpw
Text Generation • 449B • Updated • 5.58k • 2
avlp12/Motif-3-Alis-MLX-8bit
Text Generation • 89B • Updated • 249 • 2
avlp12/Motif-3-Alis-MLX-4.5bpw
Text Generation • 50B • Updated • 425
avlp12/Solar-Open2-250B-Alis-MLX-Dynamic
Text Generation • 250B • Updated • 543 • 1
avlp12/Motif-3-Beta-Alis-MLX-8bit
Text Generation • 315B • Updated • 870 • 2
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-4.5bpw
Text Generation • 315B • Updated • 301 • 1
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw
Text Generation • 315B • Updated • 469 • 3
datasets 0
None public yet