LLM Name | Qwen3 4B Instruct 2507 8bit |
Repository ๐ค | https://huggingface.co/mlx-community/Qwen3-4B-Instruct-2507-8bit |
Base Model(s) | |
Model Size | 4b |
Required VRAM | 4.3 GB |
Updated | 2025-09-23 |
Maintainer | mlx-community |
Model Type | qwen3 |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 8bit |
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 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...Instruct 2507 Unsloth Bnb 4bit | 256K / 3.5 GB | 64931 | 4 |
Qwen3 4B Instruct 2507 4bit | 256K / 2.3 GB | 2930 | 5 |
...wen3 4B Instruct 2507 Sft Full | 256K / 8.1 GB | 5 | 0 |
... Instruct F16 6B Brainstorm20x | 40K / 11.9 GB | 12 | 0 |
Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 1473674 | 320 |
...wen3 4B Toolcalling Gguf Codex | 256K / 4.3 GB | 594 | 13 |
WEBGEN 4B Preview | 256K / 8.1 GB | 1476 | 80 |
Qwen3 4B Instruct 2507 FP8 | 256K / 5.2 GB | 41542 | 31 |
Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 44289 | 10 |
...B Toolcall Gguf Llamacpp Codex | 256K / 4.3 GB | 82 | 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