LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3.5 122B A10B OptiQ 2bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3.5 122B A10B OptiQ 2bit   URL Share it on

  115   

Qwen3.5 122B A10B OptiQ 2bit is an open-source language model by mlx-community. Features: 122b LLM, VRAM: 46.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.

  2bit   4-bit   Apple-silicon Base model:mlx-community/qwen3... Base model:quantized:mlx-commu...   Conversational   Mixed-precision   Mlx   Moe   Optiq   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Ssd-streaming   Static   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit 

Qwen3.5 122B A10B OptiQ 2bit Benchmarks

LLME Score: 0.32892
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3.5 122B A10B OptiQ 2bit (mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit)
🌟 Advertise your project 🚀

Qwen3.5 122B A10B OptiQ 2bit Parameters and Internals

LLM NameQwen3.5 122B A10B OptiQ 2bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit 
Base Model(s)  mlx-community/Qwen3.5-122B-A10B-bf16   mlx-community/Qwen3.5-122B-A10B-bf16
Model Size122b
Required VRAM46.1 GB
Updated2026-06-21
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.2 GB: 1-of-9   5.3 GB: 2-of-9   5.4 GB: 3-of-9   5.4 GB: 4-of-9   5.2 GB: 5-of-9   5.4 GB: 6-of-9   5.4 GB: 7-of-9   5.1 GB: 8-of-9   3.7 GB: 9-of-9
Quantization Type2bit
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 OptiQ 2bit

Best Alternatives
Context / RAM
Downloads
Likes
...3.5 122B A10B GameDev MLX 4bit0K / 44.4 GB23934
...22B A10B Vision MLX Mixed 4bit0K / 4.7 GB440
Qwen3.5 122B A10B NVFP40K / 83.5 GB125
Qwen3.5 REAP 97B A10B0K / 194.2 GB2617
Qwen3.5 122B A10B Abliterated0K / 248.6 GB525
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit.

Rank the Qwen3.5 122B A10B OptiQ 2bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 54454 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer