Phi 4 Mini Reasoning Unsloth Bnb 4bit is an open-source language model by unsloth. Features: 3.9b LLM, VRAM: 3GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.22.
4-bit 4bit Base model:microsoft/phi-4-min... Base model:quantized:microsoft... Bitsandbytes Code Conversational En Endpoints compatible Math Phi3 Quantized Region:us Safetensors Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Phi-4-mini-reasoning-unsloth-bnb-4bit
Phi 4 Mini Reasoning Unsloth Bnb 4bit 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 Mini Reasoning Unsloth Bnb 4bit Parameters and Internals
| LLM Name | Phi 4 Mini Reasoning Unsloth Bnb 4bit |
| Repository 🤗 | https://huggingface.co/unsloth/Phi-4-mini-reasoning-unsloth-bnb-4bit |
| Base Model(s) | |
| Model Size | 3.9b |
| Required VRAM | 3 GB |
| Updated | 2026-03-29 |
| Maintainer | unsloth |
| Model Type | phi3 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.52.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endofprompt|> |
| Vocabulary Size | 200064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 4 Mini Reasoning Unsloth Bnb 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Mini Instruct Unsloth Bnb 4bit | 128K / 3.2 GB | 11917 | 22 |
| Phi 4 Mini Instruct Bnb 4bit | 128K / 2.9 GB | 5034 | 4 |
| Phi 4 Mini Instruct Bnb 4bit | 128K / 2.9 GB | 25 | 0 |
| ...hi 3 Medium 128K Instruct 8bit | 128K / 14.9 GB | 12 | 2 |
| ...Mini 128K Instruct 4bit 64rank | 128K / 2.4 GB | 10 | 0 |
| Phi 3 Medium 4K Instruct 8bit | 4K / 14.9 GB | 5 | 0 |
| ...hi 3 Mini 4K Instruct Bnb 4bit | 4K / 2.3 GB | 65 | 6 |
| Phi 3 Mini 4K Instruct Q4 | 4K / 2.3 GB | 3 | 1 |
| ...um 128K Instruct GPTQ 8 Bit C4 | 128K / 14.6 GB | 8 | 0 |
| ...edium 128K Instruct GPTQ 8 Bit | 128K / 14.6 GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Phi-4-mini-reasoning-unsloth-bnb-4bit .
Rank the Phi 4 Mini Reasoning Unsloth Bnb 4bit 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? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a