LLM Name | Qwen3 235B A22B Instruct 2507 3bit DWQ |
Repository ๐ค | https://huggingface.co/mlx-community/Qwen3-235B-A22B-Instruct-2507-3bit-DWQ |
Base Model(s) | |
Model Size | 235b |
Required VRAM | 103 GB |
Updated | 2025-07-29 |
Maintainer | mlx-community |
Model Type | qwen3_moe |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 8bit |
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 |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...5B A22B Instruct 2507 4bit DWQ | 256K / 131.4 GB | 436 | 3 |
...3 235B A22B Instruct 2507 4bit | 256K / 131.4 GB | 309 | 3 |
...3 235B A22B Instruct 2507 8bit | 256K / 227.7 GB | 211 | 0 |
Qwen3 235B A22B Instruct 2507 | 256K / 471 GB | 15135 | 541 |
...n3 235B A22B Instruct 2507 FP8 | 256K / 236.5 GB | 14644 | 100 |
...n3 235B A22B Instruct 2507 AWQ | 256K / 124.1 GB | 554 | 4 |
Qwen3 235B A22B Instruct 2507 | 256K / 471 GB | 93 | 6 |
...n3 235B A22B Instruct 2507 FP8 | 256K / 236.5 GB | 126 | 2 |
๐ 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! ๐