LLM Name | Qwen3 4B Base Unsloth Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/Qwen3-4B-Base-unsloth-bnb-4bit |
Base Model(s) | |
Model Size | 4b |
Required VRAM | 3.3 GB |
Updated | 2025-09-20 |
Maintainer | unsloth |
Model Type | qwen3 |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Qwen3ForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.51.3 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|vision_pad|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Zeta Qwen3 4B Sft | 0 | 28 | 8 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...wen3 4B Thinking 2507 MLX 8bit | 256K / 4.3 GB | 728943 | 7 |
...wen3 4B Thinking 2507 MLX 4bit | 256K / 2.3 GB | 742823 | 4 |
...Instruct 2507 Unsloth Bnb 4bit | 256K / 3.5 GB | 66759 | 3 |
...Thinking 2507 Unsloth Bnb 4bit | 256K / 3.5 GB | 17642 | 2 |
Qwen3 4B Instruct 2507 4bit | 256K / 2.3 GB | 2528 | 5 |
Qwen3 4B Thinking 2507 4bit | 256K / 2.3 GB | 2747 | 2 |
Jan V1 4B 8bit | 256K / 4.3 GB | 213 | 3 |
Qwen3 4B Instruct 2507 8bit | 256K / 4.3 GB | 103 | 4 |
Qwen3 4B Thinking 2507 Sft | 256K / 8.1 GB | 7 | 0 |
...wen3 4B Instruct 2507 Sft Full | 256K / 8.1 GB | 6 | 0 |
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