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 6 hours ago
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw updated a model about 6 hours ago
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-4.5bpw updated a model about 6 hours ago
avlp12/Motif-3-Beta-Alis-MLX-8bitOrganizations
None yet
models 37
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw
Text Generation • 25B • Updated • 347 • 3
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-4.5bpw
Text Generation • 50B • Updated • 218 • 1
avlp12/Motif-3-Beta-Alis-MLX-8bit
Text Generation • 89B • Updated • 365 • 2
avlp12/dsv4flash-mtp-aligned
Updated
avlp12/Qwen3.8-27B-Alis-MLX-8bit
Image-Text-to-Text • 8B • Updated • 1.71k • 6
avlp12/Qwen3.8-27B-Alis-MLX-6bit
Image-Text-to-Text • 7B • Updated • 841 • 1
avlp12/Qwen3.8-27B-Alis-MLX-4bit
Image-Text-to-Text • 5B • Updated • 1.31k • 4
avlp12/Kimi-K3-Alis-MLX-Dynamic-2.10bpw
Text Generation • 449B • Updated • 6.11k • 2
avlp12/Motif-3-Alis-MLX-8bit
Text Generation • 89B • Updated • 268 • 1
avlp12/Motif-3-Alis-MLX-4.5bpw
Text Generation • 50B • Updated • 449
datasets 0
None public yet