LLM Name | Qwen3 32B |
Repository ๐ค | https://huggingface.co/Qwen/Qwen3-32B |
Model Size | 32b |
Required VRAM | 65.6 GB |
Updated | 2025-07-25 |
Maintainer | Qwen |
Model Type | qwen3 |
Model Files | |
Model Architecture | Qwen3ForCausalLM |
License | apache-2.0 |
Context Length | 40960 |
Model Max Length | 40960 |
Transformers Version | 4.51.0 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Qwen3 32B AWQ | 89 | 603784 | 19 GB |
Qwen3 32B GGUF | 78 | 27774 | 7 GB |
Qwen3 32B Unsloth Bnb 4bit | 12 | 13348 | 39 GB |
Qwen3 32B 128K GGUF | 24 | 5865 | 7 GB |
Qwen3 32B 4bit | 1 | 936 | 18 GB |
Qwen3 32B 8bit | 0 | 882 | 34 GB |
Qwen3 32B AWQ | 3 | 630 | 19 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...ll Qwen3 32B Preview6 QAT 200K | 195K / 65.8 GB | 18 | 2 |
...ll Qwen3 32B Preview4 QAT 200K | 195K / 65.8 GB | 17 | 1 |
T Pro It 2.0 | 40K / 65.8 GB | 2722 | 102 |
DeepSWE Preview | 40K / 131.6 GB | 10666 | 165 |
Qwen3 32B FP8 | 40K / 34.5 GB | 176797 | 56 |
Qwen3 32B | 40K / 65.8 GB | 23475 | 10 |
...Distill Qwen3 32B Preview0 QAT | 40K / 65.8 GB | 334 | 38 |
Qwen3 72B Embiggened | 40K / 146 GB | 279 | 18 |
Qwen3 32B MLX Bf16 | 40K / 65.2 GB | 505 | 5 |
...Distill Qwen3 32B Preview2 QAT | 40K / 65.8 GB | 124 | 13 |
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