Phi 4 Mini 6B Merge is an open-source language model by Pinkstack. Features: 6b LLM, VRAM: 12.5GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.19.
Base model:merge:microsoft/phi... Base model:merge:microsoft/phi... Base model:microsoft/phi-4-min... Base model:microsoft/phi-4-min... Conversational Custom code Endpoints compatible Instruct Merge Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Pinkstack/Phi-4-mini-6b-merge
Phi 4 Mini 6B Merge 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 6B Merge Parameters and Internals
| LLM Name | Phi 4 Mini 6B Merge |
| Repository 🤗 | https://huggingface.co/Pinkstack/Phi-4-mini-6b-merge |
| Base Model(s) | |
| Model Size | 6b |
| Required VRAM | 12.5 GB |
| Updated | 2026-05-01 |
| Maintainer | Pinkstack |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 200064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 4 Mini 6B Merge
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi3 128K 6B | 128K / 11.8 GB | 4 | 2 |
| Phi 3 6B 4K Instruct | 4K / 12.2 GB | 9 | 2 |
Rank the Phi 4 Mini 6B Merge 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? 53651 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