LLM Name | Qwen3 4B Thinking 2507 |
Repository ๐ค | https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507 |
Model Size | 4b |
Required VRAM | 8.1 GB |
Updated | 2025-08-09 |
Maintainer | Qwen |
Model Type | qwen3 |
Model Files | |
Model Architecture | Qwen3ForCausalLM |
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 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...wen3 4B Thinking 2507 MLX 8bit | 6 | 1430 | 4 GB |
...wen3 4B Thinking 2507 MLX 4bit | 2 | 511 | 2 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 19483 | 156 |
Qwen3 4B Thinking 2507 FP8 | 256K / 5.2 GB | 6335 | 13 |
Qwen3 4B Instruct 2507 FP8 | 256K / 5.2 GB | 1639 | 16 |
Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 491 | 2 |
Qwen3 4B Thinking 2507 | 256K / 8.1 GB | 352 | 2 |
Jan Nano 128K | 128K / 8.1 GB | 2716 | 208 |
Polaris 4B Preview | 128K / 8.1 GB | 2249 | 129 |
Jan Nano 128K | 128K / 8.1 GB | 1366 | 2 |
Nous 1 4B | 128K / 8.1 GB | 143 | 3 |
Nous V1 4B | 128K / 8.1 GB | 75 | 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