Receipt-sealed layer-local ALIS-DWQ MLX quants of Inkling 975B multimodal MoE, built on 2x512GB M3 Ultra. Quality 3.7 / capacity 2.7 bpw / Q6 soon.
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 about 6 hours ago
Inkling 975B · Alis MLX Dynamic updated a collection about 6 hours ago
Inkling 975B · Alis MLX DynamicOrganizations
None yet
models 24
avlp12/Inkling-975B-Alis-MLX-Dynamic-2.7bpw
Image-Text-to-Text • 947B • Updated
avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw
Image-Text-to-Text • 947B • Updated • 104 • 1
avlp12/Qwen3.6-35B-A3B-Alis-MLX-Dynamic
Image-Text-to-Text • 36B • Updated • 494 • 1
avlp12/ThinkingCap-Qwen3.6-27B-Alis-MLX-Dynamic
Image-Text-to-Text • 28B • Updated • 941 • 3
avlp12/Qwen3.6-27B-Alis-MLX-Dynamic
Image-Text-to-Text • 28B • Updated • 317
avlp12/MiniMax-M3-Alis-MLX-Dynamic
Image-Text-to-Text • 427B • Updated • 768
avlp12/Hy3-Alis-MLX-Dynamic
Text Generation • 295B • Updated • 3.22k • 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 • 234
datasets 0
None public yet