LLM EXPLORER 58,975 MODELS INDEXED

Qwen3.5 122B A10B 4bit by mlx-community

By mlx-community · 14412 downloads
HF Repo ↗ Copy URL

Qwen3.5 122B A10B 4bit is an open-source language model by mlx-community. Features: 122b LLM, VRAM: 69.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

  4-bit   4bit   Conversational   Endpoints compatible   Image-text-to-text   Mlx   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit 

Qwen3.5 122B A10B 4bit Parameters and Internals

LLM NameQwen3.5 122B A10B 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit 
Model Size122b
Required VRAM69.5 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.1 GB: 1-of-14   5.2 GB: 2-of-14   5.2 GB: 3-of-14   5.1 GB: 4-of-14   5.2 GB: 5-of-14   5.2 GB: 6-of-14   5.1 GB: 7-of-14   5.2 GB: 8-of-14   5.2 GB: 9-of-14   5.1 GB: 10-of-14   5.2 GB: 11-of-14   5.2 GB: 12-of-14   5.2 GB: 13-of-14   2.3 GB: 14-of-14
Quantization Type4bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 122B A10B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 122B A10B 8bit0K / 129.7 GB41242
Qwen3.5 122B A10B OptiQ 2bit0K / 46.1 GB10934
Qwen3.5 122B A10B 6bit0K / 100.1 GB38463
...3.5 122B A10B GameDev MLX 4bit0K / 44.4 GB3594
Qwen3.5 122B A10B 5bit0K / 85.2 GB6542
...22B A10B Vision MLX Mixed 4bit0K / 4.7 GB440
Qwen3.5 122B A10B NVFP40K / 83.5 GB24873249
Qwen3.5 122B A10B0K / 248.6 GB2139628605
Qwen3.5 122B A10B0K / 248.6 GB451
Qwen3.5 122B A10B0K / 248.6 GB16808
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-122B-A10B-4bit.