LLM EXPLORER 60,062 MODELS INDEXED

Qwen3.6 35B A3B 4.4bit Msq by mlx-community

By mlx-community · 67 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B 4.4bit Msq is an open-source language model by mlx-community. Features: 35b LLM, VRAM: 21.2GB, License: apache-2.0, LLM Explorer Score: 0.24.

  4-bit   Conversational   Endpoints compatible   Image-text-to-text   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-4.4bit-msq 

Qwen3.6 35B A3B 4.4bit Msq Parameters and Internals

LLM NameQwen3.6 35B A3B 4.4bit Msq
Repository 🤗https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-4.4bit-msq 
Model Size35b
Required VRAM21.2 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-5   5.2 GB: 2-of-5   5.3 GB: 3-of-5   4.9 GB: 4-of-5   0.5 GB: 5-of-5
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B 4.4bit Msq

Best Alternatives
Context / RAM
Downloads
Likes
Ornith 1.5 35B A3B NPU2256K /  GB1421
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Ornith 1.0 35B0K / 70.4 GB3045441504
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Ornith 1.5 35B A3B0K / 72.1 GB1713201
Qwen3.6 35B A3B NVFP4 Fast0K / 23.6 GB46366198
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.6-35B-A3B-4.4bit-msq.