Qwen-3.6-unsloth-mlx
Collection
AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 18 items • Updated • 19
Lukas Wolfsteiner
dotwee
·
AI & ML interests
🇪🇺 eu/acc | Professional Software Engineer specialised in Digital Health @ adesso Schweiz AG; shaping resilient Software Architectures and cultivating flourishing Codebases
Recent Activity
updated a model 1 day ago
dotwee/Qwythos-9B-Claude-Mythos-5-1M-mlx-4bit published a model 1 day ago
dotwee/Qwythos-9B-Claude-Mythos-5-1M-mlx-4bit updated a model 1 day ago
dotwee/Qwythos-9B-Claude-Mythos-5-1M-mlx-6bitOrganizations
upvoted a collection about 2 months ago