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
updated a model about 12 hours ago
avlp12/Motif-3-Beta-Alis-MLX-8bit updated a model about 14 hours ago
avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw updated a model about 14 hours ago
avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw-VLMOrganizations
None yet
models 37
avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw
Text Generation • 73B • Updated • 653 • 2
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-4.5bpw
Text Generation • Updated • 159 • 1
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw
Text Generation • Updated • 306 • 3
avlp12/Motif-3-Beta-Alis-MLX-8bit
Text Generation • Updated • 183 • 2
avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw
Text Generation • Updated • 651 • 2
avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw-VLM
Image-Text-to-Text • 133B • Updated • 1.05k • 2
avlp12/dsv4flash-mtp-aligned
Updated
avlp12/Qwen3.8-27B-Alis-MLX-8bit
Image-Text-to-Text • 8B • Updated • 1.87k • 6
avlp12/Qwen3.8-27B-Alis-MLX-6bit
Image-Text-to-Text • 7B • Updated • 902 • 1
avlp12/Qwen3.8-27B-Alis-MLX-4bit
Image-Text-to-Text • 5B • Updated • 1.46k • 4
datasets 0
None public yet