Arxiv:2504.21233 Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-4-min... Chat Code Conversational Dataset:bifrost-ai/solana-vang... En Endpoints compatible Finance Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Bifrost-AI/Phi-4-Mirage-sol-Reasoning-3.8B
Phi 4 Mirage Sol Reasoning 3.8B 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 4 Mirage Sol Reasoning 3.8B Parameters and Internals
| LLM Name | Phi 4 Mirage Sol Reasoning 3.8B |
| Repository 🤗 | https://huggingface.co/Bifrost-AI/Phi-4-Mirage-sol-Reasoning-3.8B |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.7 GB |
| Updated | 2025-07-19 |
| Maintainer | Bifrost-AI |
| Model Type | phi3 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.53.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 200064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 4 Mirage Sol Reasoning 3.8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini Instruct | 128K / 7.7 GB | 243538 | 553 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 525241 | 1655 |
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 195074 | 891 |
| Phi 4 Mini Reasoning | 128K / 7.7 GB | 31351 | 192 |
| MediPhi Instruct | 128K / 7.7 GB | 320 | 12 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 4 Mini Reasoning | 128K / 7.7 GB | 1787 | 2 |
| Phi 4 Mini Instruct | 128K / 7.7 GB | 4328 | 17 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 8 | 0 |
| MediPhi Clinical | 128K / 7.7 GB | 204 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Bifrost-AI/Phi-4-Mirage-sol-Reasoning-3.8B .
Rank the Phi 4 Mirage Sol Reasoning 3.8B 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? 49901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124