What are the hardware requirements for Phi 4 Bnb 4bit?

Phi 4 Bnb 4bit requires approximately 9.1 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 4 Bnb 4bit and how large is it?

Phi 4 Bnb 4bit is developed by unsloth, a model with 15.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Phi 4 Bnb 4bit?

Phi 4 Bnb 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 4 Bnb 4bit by unsloth — VRAM 9.1GB, 16K context

Name: Phi 4 Bnb 4bit
Author: unsloth

Phi 4 Bnb 4bit is an open-source language model by unsloth. Features: 15.1b LLM, VRAM: 9.1GB, Context: 16K, License: mit, Quantized, LLM Explorer Score: 0.31.

Arxiv:2412.08905 4-bit 4bit Base model:microsoft/phi-4 Base model:quantized:microsoft... Bitsandbytes Chat Code Conversational Deploy:azure En Endpoints compatible Llama Math Phi Phi4 Quantized Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/unsloth/phi-4-bnb-4bit

Phi 4 Bnb 4bit Benchmarks

LLME Score: 0.30978

^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)

🌟 Advertise your project 🚀

Phi 4 Bnb 4bit Parameters and Internals

LLM Name	Phi 4 Bnb 4bit
Repository 🤗	https://huggingface.co/unsloth/phi-4-bnb-4bit
Base Model(s)	Phi 4 microsoft/phi-4
Model Size	15.1b
Required VRAM	9.1 GB
Updated	2026-05-10
Maintainer	unsloth
Model Type	llama
Model Files	5.0 GB: 1-of-2 4.1 GB: 2-of-2
Supported Languages	en
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	mit
Context Length	16384
Model Max Length	16384
Transformers Version	4.47.1
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|dummy_87\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Quantized Models of the Phi 4 Bnb 4bit

Model	Likes	Downloads	VRAM
DeepThink Phi4	1	24	29 GB
DeepThinkers Phi4	5	0	29 GB
Phi 4 14B Grpo Limo	0	77	29 GB
Phi 4 14B Grpo Gsm8k 3e	0	28	29 GB
...APhi4 GRPO 250218 Merged 16bit	0	10	29 GB

Best Alternatives to Phi 4 Bnb 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Phi 4 Unsloth Bnb 4bit	16K / 10.4 GB	11462	64

Note: green Score (e.g. "73.2") means that the model is better than unsloth/phi-4-bnb-4bit.

Rank the Phi 4 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! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Phi 4 Bnb 4bit by unsloth