Qwen3 235B A22B MLX 6bit by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen3 235B A22B MLX 6bit   URL Share it on

  Arxiv:2309.00071   Arxiv:2505.09388   6-bit   6bit   Conversational   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow

Qwen3 235B A22B MLX 6bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 235B A22B MLX 6bit (Qwen/Qwen3-235B-A22B-MLX-6bit)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 235B A22B MLX 6bit Parameters and Internals

LLM NameQwen3 235B A22B MLX 6bit
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen3-235B-A22B-MLX-6bit 
Model Size235b
Required VRAM184.3 GB
Updated2025-07-02
MaintainerQwen
Model Typeqwen3_moe
Model Files  5.1 GB: 1-of-36   5.2 GB: 2-of-36   5.2 GB: 3-of-36   5.2 GB: 4-of-36   5.2 GB: 5-of-36   5.2 GB: 6-of-36   5.2 GB: 7-of-36   5.2 GB: 8-of-36   5.2 GB: 9-of-36   5.2 GB: 10-of-36   5.2 GB: 11-of-36   5.2 GB: 12-of-36   5.2 GB: 13-of-36   5.2 GB: 14-of-36   5.2 GB: 15-of-36   5.2 GB: 16-of-36   5.2 GB: 17-of-36   5.2 GB: 18-of-36   5.2 GB: 19-of-36   5.2 GB: 20-of-36   5.2 GB: 21-of-36   5.2 GB: 22-of-36   5.2 GB: 23-of-36   5.2 GB: 24-of-36   5.2 GB: 25-of-36   5.2 GB: 26-of-36   5.2 GB: 27-of-36   5.2 GB: 28-of-36   5.2 GB: 29-of-36   5.2 GB: 30-of-36   5.2 GB: 31-of-36   5.2 GB: 32-of-36   5.2 GB: 33-of-36   5.2 GB: 34-of-36   5.2 GB: 35-of-36   2.4 GB: 36-of-36
Quantization Type6bit
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3 235B A22B MLX 6bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 235B A22B 4bit40K / 131.4 GB1376437
Qwen3 235B A22B 8bit40K / 238.3 GB1374852
Qwen3 235B A22B MLX 4bit40K / 125.2 GB4709
Qwen3 235B A22B 3bit DWQ40K / 117.4 GB20833
Qwen3 235B A22B 4bit DWQ40K / 131.4 GB18692
Qwen3 235B A22B Mixed 3 6bit40K / 117 GB19653
Qwen3 235B A22B MLX 8bit40K / 234.4 GB2415
...wen3 235B A22B 4bit DWQ 05312540K / 131.4 GB5992
Qwen3 235B A22B 128K GGUF128K /  GB1420931
Qwen3 235B A22B40K / 179.9 GB143594964
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-235B-A22B-MLX-6bit.

Rank the Qwen3 235B A22B MLX 6bit Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 49328 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124