8-bit Autotrain compatible Bitsandbytes Conversational Custom code Endpoints compatible Instruct Phi3 Q8 Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Caltert/ph3_q8
Ph3 Q8 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Ph3 Q8 Parameters and Internals
| LLM Name | Ph3 Q8 |
| Repository 🤗 | https://huggingface.co/Caltert/ph3_q8 |
| Model Size | 3.8b |
| Required VRAM | 4 GB |
| Updated | 2025-07-29 |
| Maintainer | Caltert |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | q8 |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Ph3 Q8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini Instruct | 128K / 7.7 GB | 232977 | 560 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 827074 | 1656 |
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 170597 | 894 |
| MediPhi Instruct | 128K / 7.7 GB | 2260 | 32 |
| NuExtract 1.5 | 128K / 7.7 GB | 35302 | 236 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 4 Mini Instruct | 128K / 7.7 GB | 4336 | 18 |
| MediPhi Clinical | 128K / 7.7 GB | 432 | 6 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 5 | 0 |
| MediPhi MedCode | 128K / 7.7 GB | 289 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Caltert/ph3_q8 .
Rank the Ph3 Q8 Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 50230 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124