Anton Kuzmenko

default-anton's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 3 days ago

NVIDIA NVFP4 → MLX

Collection

NVIDIA post-trained NVFP4 checkpoints (ModelOpt PTQ) transcoded to MLX for Apple Silicon / mlx-node, keeping NVIDIA's per-layer bit allocation. • 2 items • Updated 4 days ago • 3

upvoted a collection 3 months ago

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 May 15 • 19