LLM Name | FluentlyQwen3 Coder 4B 0909 |
Repository ๐ค | https://huggingface.co/fluently/FluentlyQwen3-Coder-4B-0909 |
Base Model(s) | |
Model Size | 4b |
Required VRAM | 8 GB |
Updated | 2025-09-10 |
Maintainer | fluently |
Model Type | qwen3 |
Model Files | |
Supported Languages | en ru code |
Generates Code | Yes |
Model Architecture | Qwen3ForCausalLM |
License | apache-2.0 |
Context Length | 40960 |
Model Max Length | 40960 |
Transformers Version | 4.55.4 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | float16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Bootes Qwen3 Coder Reasoning | 40K / 8.1 GB | 1169 | 7 |
FluentlyQwen3 Coder 4B | 40K / 8 GB | 8 | 0 |
...tzar Coder F1 6B Brainstorm20x | 40K / 11.9 GB | 16 | 3 |
...ODER Instruct 6B Brainstorm20x | 40K / 11.9 GB | 15 | 0 |
...DER Instruct 12B Brainstorm20x | 40K / 47.3 GB | 15 | 0 |
Blitzar Coder 4B F.1 | 40K / 8.1 GB | 19 | 7 |
Qwen3 4B NexusPrime | 40K / 8.2 GB | 8 | 5 |
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