| Model Type | 
 | |
| Additional Notes | 
 | |
| Supported Languages | 
 | 
| LLM Name | Phi 3 Medium 4K Instruct 8bit | 
| Repository ๐ค | https://huggingface.co/mlx-community/Phi-3-medium-4k-instruct-8bit | 
| Model Size | 3.9b | 
| Required VRAM | 14.9 GB | 
| Updated | 2025-09-23 | 
| Maintainer | mlx-community | 
| Model Type | phi3 | 
| Instruction-Based | Yes | 
| Model Files | |
| Quantization Type | 8bit | 
| Model Architecture | Phi3ForCausalLM | 
| License | mit | 
| Context Length | 4096 | 
| Model Max Length | 4096 | 
| Transformers Version | 4.39.3 | 
| Tokenizer Class | LlamaTokenizer | 
| Padding Token | <|endoftext|> | 
| Vocabulary Size | 32064 | 
| Torch Data Type | bfloat16 | 
| Best Alternatives | Context / RAM | Downloads | Likes | 
|---|---|---|---|
| ...hi 3 Medium 128K Instruct 8bit | 128K / 14.9 GB | 13 | 2 | 
| ...um 128K Instruct GPTQ 8 Bit C4 | 128K / 14.6 GB | 8 | 0 | 
| ...edium 128K Instruct GPTQ 8 Bit | 128K / 14.6 GB | 8 | 0 | 
| ... Medium 4K Instruct 8 Bit Gptq | 4K / 14.6 GB | 0 | 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