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

liked a Space 20 days ago

Running

Featured

29

ColBERT Tool Selection

🧭

29

Send a request, the retriever pre-selects the right tools

liked 2 models 21 days ago

LiquidAI/LFM2.5-Embedding-350M

Sentence Similarity • 0.4B • Updated 19 days ago • 33.7k • 131

LiquidAI/LFM2.5-ColBERT-350M

Sentence Similarity • 0.4B • Updated 20 days ago • 11.6k • 104

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

liked a Space 10 months ago

Running

Featured

683

The Tokenizer Playground

📝

683

Experiment with and compare different tokenizers