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 | 2025-07-25 |
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 |
---|---|---|---|
Qwen3 4B MLX 4bit | 64K / 2.1 GB | 266 | 3 |
Qwen3 4B Unsloth Bnb 4bit | 40K / 3.6 GB | 68553 | 9 |
Qwen3 4B 4bit | 40K / 2.3 GB | 5871 | 7 |
Qwen3 4B 4bit DWQ 053125 | 40K / 2.3 GB | 1474 | 2 |
...incot DPO 0720 Dataset V5 Dsr1 | 40K / 8.1 GB | 41 | 0 |
Qwen3 4B 4bit DWQ | 40K / 2.3 GB | 926 | 4 |
...d Qwen3 4B Abliterated V1 4bit | 40K / 2.3 GB | 964 | 2 |
Qwen3 4B MLX 8bit | 40K / 4.2 GB | 189 | 2 |
...d Qwen3 4B Abliterated V1 6bit | 40K / 3.3 GB | 69 | 2 |
Qwen3 4B 3kingdoms Augmented | 40K / 8.1 GB | 5 | 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