Arxiv:1910.09700 4-bit Autotrain compatible Conversational Custom code Endpoints compatible Gptq Instruct Phi3 Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/SotiriosKastanas/microsoft-Phi-3-medium-4k-instruct-4-bit-gptq
Microsoft Phi 3 Medium 4K Instruct 4 Bit Gptq 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)
Microsoft Phi 3 Medium 4K Instruct 4 Bit Gptq Parameters and Internals
| LLM Name | Microsoft Phi 3 Medium 4K Instruct 4 Bit Gptq |
| Repository 🤗 | https://huggingface.co/SotiriosKastanas/microsoft-Phi-3-medium-4k-instruct-4-bit-gptq |
| Model Size | 2.2b |
| Required VRAM | 7.7 GB |
| Updated | 2025-02-05 |
| Maintainer | SotiriosKastanas |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Microsoft Phi 3 Medium 4K Instruct 4 Bit Gptq
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...3 Medium 4K Instruct Gptq 4bit | 4K / 7.8 GB | 104 | 2 |
| ...hi 3 Medium 128K Instruct 4bit | 128K / 7.8 GB | 13 | 2 |
| Phi 3 Medium 4K Instruct 4bit | 4K / 7.8 GB | 6 | 0 |
| Phi 3 Medium 128K Instruct AWQ | 128K / 7.8 GB | 22 | 1 |
| ... Medium 128K Instruct AWQ 4bit | 128K / 7.8 GB | 0 | 0 |
| ... 3 Medium 4K Instruct AWQ 4bit | 4K / 7.8 GB | 0 | 0 |
Rank the Microsoft Phi 3 Medium 4K Instruct 4 Bit Gptq 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227