Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-m... Custom code En Instruct Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/meditsolutions/MedIT-Mesh-3B-Instruct
MedIT Mesh 3B Instruct Benchmarks
MMLU Pro: 33.46
GPQA: 9.84
MUSR: 10.6
BBH: 37.55
IFEval: 58.14 vs 88 (so35)-33.9%
MATH Lvl 5: 20.32
LLME Score: 0.2642
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)
MedIT Mesh 3B Instruct Parameters and Internals
| LLM Name | MedIT Mesh 3B Instruct |
| Repository 🤗 | https://huggingface.co/meditsolutions/MedIT-Mesh-3B-Instruct |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 7.7 GB |
| Updated | 2025-10-14 |
| Maintainer | meditsolutions |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives to MedIT Mesh 3B Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ocolatine 3B Instruct DPO V1.2 | 128K / 7.7 GB | 2503 | 9 |
| ILAB Merging 3B V2 | 128K / 23.1 GB | 3 | 2 |
| 3Bgeneral ECE PRYMMAL Martial | 128K / 7.7 GB | 5 | 0 |
| 3Blareneg ECE PRYMMAL Martial | 128K / 7.7 GB | 7 | 0 |
| ECE EIFFEL 3B | 128K / 7.7 GB | 5 | 0 |
| Chocolatine Admin 3B SFT V0.3B | 128K / 7.7 GB | 3 | 4 |
| ECE GRENELLE 3B | 128K / 7.7 GB | 59 | 0 |
| Phi3 3B Ultrachat Svd Model | 128K / 7.7 GB | 1 | 1 |
| Orpo Phi3 3B 128K | 128K / 7.7 GB | 8 | 3 |
| ECE PRYMMAL 3B SLERP 2 V1 | 4K / 7.7 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than meditsolutions/MedIT-Mesh-3B-Instruct .
Rank the MedIT Mesh 3B Instruct 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124