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

Unsloth Phi 4 4bit requires approximately 8.3 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 Unsloth Phi 4 4bit and how large is it?

Unsloth Phi 4 4bit is developed by mlx-community, a model with 2.3b 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 Unsloth Phi 4 4bit?

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

Unsloth Phi 4 4bit by mlx-community — VRAM 8.3GB, 16K context

Name: Unsloth Phi 4 4bit
Author: mlx-community

Unsloth Phi 4 4bit is an open-source language model by mlx-community. Features: 2.3b LLM, VRAM: 8.3GB, Context: 16K, License: mit, Quantized, LLM Explorer Score: 0.16.

4-bit 4bit Base model:quantized:unsloth/p... Base model:unsloth/phi-4 Chat Code Conversational En Endpoints compatible Llama Math Mlx Phi Phi4 Quantized Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/mlx-community/Unsloth-Phi-4-4bit

Unsloth Phi 4 4bit Parameters and Internals

LLM Name	Unsloth Phi 4 4bit
Repository 🤗	https://huggingface.co/mlx-community/Unsloth-Phi-4-4bit
Base Model(s)	Phi 4 unsloth/phi-4
Model Size	2.3b
Required VRAM	8.3 GB
Updated	2026-07-05
Maintainer	mlx-community
Model Type	llama
Model Files	5.4 GB: 1-of-2 2.9 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

Rank the Unsloth Phi 4 4bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Unsloth Phi 4 4bit

Best Alternatives	Context / RAM	Downloads	Likes
... Text Chat 512K 6.0bpw H6 EXL2	512K / 5.2 GB	6	1
... Text Chat 512K 5.0bpw H6 EXL2	512K / 4.4 GB	1	1
Slimorca Phi 3.5	128K / 7.6 GB	7	0
Phi 3.5 Instruct Vul	128K / 7.6 GB	17	0
... Text Chat 128K 6.0bpw H6 EXL2	128K / 5.2 GB	3	1
QuantumQuill	16K / 2.2 GB	5	0
...ocalAI Functioncall Phi 4 V0.3	16K / 29.4 GB	91	10
...ocalAI Functioncall Phi 4 V0.3	16K / 29.4 GB	6	8
PARM V2 Phi 4 4K CoT PyTorch	16K / 29.4 GB	0	1
CodeMate V0.1 6.0bpw H6 EXL2	16K / 25.7 GB	1	1

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Unsloth-Phi-4-4bit.