Arxiv:2505.09388 Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen3-235b-a22... Conversational Endpoints compatible Fp8 Instruct Qwen3 moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8
Qwen3 235B A22B Instruct 2507 FP8 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen3 235B A22B Instruct 2507 FP8 Parameters and Internals
| LLM Name | Qwen3 235B A22B Instruct 2507 FP8 |
| Repository 🤗 | https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 |
| Base Model(s) | |
| Model Size | 235b |
| Required VRAM | 236.5 GB |
| Updated | 2025-07-22 |
| Maintainer | Qwen |
| Model Type | qwen3_moe |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen3MoeForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen3 235B A22B Instruct 2507 FP8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 235B A22B Instruct 2507 | 256K / 471 GB | 0 | 146 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 .
Rank the Qwen3 235B A22B Instruct 2507 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! 🌟
What open-source LLMs or SLMs are you in search of? 49963 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124