| LLM Name | Qwen3 SG1 10S III INSTRUCT Float32 256K Ctx 6B | 
| Repository ๐ค | https://huggingface.co/DavidAU/Qwen3-SG1-10S-III-INSTRUCT-Float32-256k-ctx-6B | 
| Base Model(s) | |
| Model Size | 6b | 
| Required VRAM | 25.3 GB | 
| Updated | 2025-09-23 | 
| Maintainer | DavidAU | 
| Model Type | qwen3 | 
| Instruction-Based | Yes | 
| Model Files | |
| Supported Languages | en | 
| Model Architecture | Qwen3ForCausalLM | 
| License | apache-2.0 | 
| Context Length | 262144 | 
| Model Max Length | 262144 | 
| Transformers Version | 4.56.1 | 
| Tokenizer Class | Qwen2Tokenizer | 
| Padding Token | <|endoftext|> | 
| Vocabulary Size | 151936 | 
| Errors | replace | 
| Best Alternatives | Context / RAM | Downloads | Likes | 
|---|---|---|---|
| ...oder Instruct 6B Brainstorm20x | 40K / 11.9 GB | 8 | 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