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 235B A22B FP8 by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 235B A22B FP8   URL Share it on

  119913   

Qwen3 235B A22B FP8 is an open-source language model by Qwen. Features: 235b LLM, VRAM: 220GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.26.

  Arxiv:2309.00071   Arxiv:2505.09388 Base model:quantized:qwen/qwen... Base model:qwen/qwen3-235b-a22...   Conversational   Endpoints compatible   Fp8   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8 

Qwen3 235B A22B FP8 Benchmarks

LLME Score: 0.26432
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 FP8 (Qwen/Qwen3-235B-A22B-FP8)
🌟 Advertise your project 🚀

Qwen3 235B A22B FP8 Parameters and Internals

LLM NameQwen3 235B A22B FP8
Repository 🤗https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8 
Base Model(s)  Qwen3 235B A22B   Qwen/Qwen3-235B-A22B
Model Size235b
Required VRAM220 GB
Updated2026-07-07
MaintainerQwen
Model Typeqwen3_moe
Model Files  5.0 GB: 1-of-48   5.0 GB: 2-of-48   5.0 GB: 3-of-48   5.0 GB: 4-of-48   5.0 GB: 5-of-48   5.0 GB: 6-of-48   5.0 GB: 7-of-48   5.0 GB: 8-of-48   5.0 GB: 9-of-48   5.0 GB: 10-of-48   5.0 GB: 11-of-48   5.0 GB: 12-of-48   5.0 GB: 13-of-48   5.0 GB: 14-of-48   5.0 GB: 15-of-48   5.0 GB: 16-of-48   5.0 GB: 17-of-48   5.0 GB: 18-of-48   5.0 GB: 19-of-48   5.0 GB: 20-of-48   5.0 GB: 21-of-48   5.0 GB: 22-of-48   5.0 GB: 23-of-48   5.0 GB: 24-of-48   5.0 GB: 25-of-48   5.0 GB: 26-of-48   5.0 GB: 27-of-48   5.0 GB: 28-of-48   5.0 GB: 29-of-48   5.0 GB: 30-of-48   5.0 GB: 31-of-48   5.0 GB: 32-of-48   5.0 GB: 33-of-48   5.0 GB: 34-of-48   5.0 GB: 35-of-48   5.0 GB: 36-of-48   5.0 GB: 37-of-48   5.0 GB: 38-of-48   5.0 GB: 39-of-48   5.0 GB: 40-of-48   5.0 GB: 41-of-48   5.0 GB: 42-of-48   5.0 GB: 43-of-48   5.0 GB: 44-of-48
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to Qwen3 235B A22B FP8

Best Alternatives
Context / RAM
Downloads
Likes
...en3 235B A22B Instruct 2507 1M986K / 171.9 GB31
Qwen3 235B A22B Instruct 2507256K / 167.9 GB1710
Qwen3 235B A22B Thinking 2507256K / 167.9 GB143
Qwen3 235B A22B Instruct 2507256K / 171.9 GB135732782
Vivo C V1256K / 156.4 GB4152
Qwen3 235B A22B Thinking 2507256K / 171.9 GB55941407
...n3 235B A22B Instruct 2507 FP8256K / 236.5 GB200233148
MiroThinker 1.7 Mini256K / 61.1 GB133799
... 235B A22B Thinking 2507 NVFP4256K / 139.2 GB228288
MiroThinker 1.7256K / 220 GB210142
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-235B-A22B-FP8.

Rank the Qwen3 235B A22B FP8 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? 55234 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