LLM EXPLORER 57,252 MODELS INDEXED

Qwen3.5 122B A10B OQ4 Mtp by mlx-community

By mlx-community · 925 downloads
HF Repo ↗ Copy URL

Qwen3.5 122B A10B OQ4 Mtp is an open-source language model by mlx-community. Features: 122b LLM, VRAM: 72.5GB, License: apache-2.0, LLM Explorer Score: 0.27.

  4-bit   Conversational   Endpoints compatible   Image-text-to-text   Mlx   Mtp   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-oQ4-mtp 

Qwen3.5 122B A10B OQ4 Mtp Parameters and Internals

LLM NameQwen3.5 122B A10B OQ4 Mtp
Repository 🤗https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-oQ4-mtp 
Model Size122b
Required VRAM72.5 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.0 GB: 1-of-14   5.4 GB: 2-of-14   5.4 GB: 3-of-14   5.4 GB: 4-of-14   5.4 GB: 5-of-14   5.4 GB: 6-of-14   5.4 GB: 7-of-14   5.4 GB: 8-of-14   5.4 GB: 9-of-14   5.4 GB: 10-of-14   5.4 GB: 11-of-14   5.4 GB: 12-of-14   5.4 GB: 13-of-14   2.7 GB: 14-of-14
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 122B A10B OQ4 Mtp

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 122B A10B NVFP40K / 83.5 GB24873249
Qwen3.5 122B A10B0K / 248.6 GB2139628605
Qwen3.5 122B A10B Abliterated0K / 248.6 GB495
Qwen3.5 122B A10B FP80K / 126.3 GB1271983112
...en3.5 122B A10B Int4 AutoRound0K / 72 GB14231145
Qwen3.5 122B A10B WMix480K / 73.2 GB2153
Qwen3.5 122B A10B WMix580K / 87.5 GB2143
Qwen3.5 122B A10B WMix680K / 102.1 GB1561
...2.6 Destill Healed Abliterated0K / 245.1 GB114315
Qwen3.5 122B A10B0K / 248.6 GB451
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-122B-A10B-oQ4-mtp.