Autotrain compatible Base model:microsoft/phi-3-med... Base model:quantized:microsoft... Code Conversational Custom code Endpoints compatible Gguf Instruct Multilingual Phi3 Q2 Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF
Phi 3 Medium 4K Instruct GGUF 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)
Phi 3 Medium 4K Instruct GGUF Parameters and Internals
| Model Type |
|
| LLM Name | Phi 3 Medium 4K Instruct GGUF |
| Repository 🤗 | https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF |
| Model Name | Phi 3 medium 4k instruct |
| Model Creator | Microsoft |
| Base Model(s) | |
| Required VRAM | 5.1 GB |
| Updated | 2025-06-09 |
| Maintainer | gaianet |
| Model Type | phi-msft |
| Instruction-Based | Yes |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf|q2|q4_k|q5_k |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.39.3 |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 3 Medium 4K Instruct GGUF
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini Instruct GGUF | 128K / 1.7 GB | 10485 | 40 |
| Phi 3 Mini 128K Instruct GGUF | 128K / 1.4 GB | 588 | 2 |
| ...hi 3 Medium 128K Instruct GGUF | 128K / 5.1 GB | 504 | 2 |
| Phi 3 Mini 128K Instruct GGUF | 128K / 1.4 GB | 467 | 1 |
| ...i 3 Mini 4K Instruct.Q4 0.gguf | 128K / 2.2 GB | 592 | 3 |
| ...hi 3 Medium 128K Instruct GGUF | 128K / 5.1 GB | 91 | 0 |
| ...i 3 Mini 4K Instruct IMat GGUF | 4K / 0.8 GB | 671 | 1 |
| Phi 3 Mini 4K Instruct GGUF | 4K / 1.4 GB | 614 | 3 |
| Phi 3 Medium 4K Instruct GGUF | 4K / 5.1 GB | 47 | 0 |
| Phi 3 Mini 128K Instruct Gguf | 0K / 1.4 GB | 579 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than gaianet/Phi-3-medium-4k-instruct-GGUF .
Rank the Phi 3 Medium 4K Instruct GGUF 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? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124