What are the hardware requirements for Phi 4 Mini Instruct Mlx Fp16?

Phi 4 Mini Instruct Mlx Fp16 requires approximately 7.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 4 Mini Instruct Mlx Fp16 and how large is it?

Phi 4 Mini Instruct Mlx Fp16 is developed by mlx-community, a model with 3.8b 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 Mini Instruct Mlx Fp16?

Phi 4 Mini Instruct Mlx Fp16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 4 Mini Instruct Mlx Fp16 by mlx-community — VRAM 7.7GB, 128K context

Name: Phi 4 Mini Instruct Mlx Fp16
Author: mlx-community

Phi 4 Mini Instruct Mlx Fp16 is an open-source language model by mlx-community. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Quantized, Instruction-Based.

Ar Base model:finetune:microsoft/... Base model:microsoft/phi-4-min... Code Conversational Cs Custom code Da De En Endpoints compatible Es Fi Fp16 Fr He Hu Instruct It Ja Ko Mlx Mlx-my-repo Multilingual Nl No Phi3 Pl Pt Quantized Region:us Ru Safetensors Sharded Sv Tensorflow Th Tr Uk Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/Phi-4-mini-instruct-mlx-fp16

Phi 4 Mini Instruct Mlx Fp16 Parameters and Internals

LLM Name	Phi 4 Mini Instruct Mlx Fp16
Repository 🤗	https://huggingface.co/mlx-community/Phi-4-mini-instruct-mlx-fp16
Base Model(s)	Phi 4 Mini Instruct microsoft/Phi-4-mini-instruct
Model Size	3.8b
Required VRAM	7.7 GB
Updated	2026-10-27
Maintainer	mlx-community
Model Type	phi3
Instruction-Based	Yes
Model Files	5.3 GB: 1-of-2 2.4 GB: 2-of-2
Supported Languages	ar zh cs da nl en fi fr de he hu it ja ko no pl pt ru es sv th tr uk
Quantization Type	fp16
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.45.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Vocabulary Size	200064
Torch Data Type	bfloat16

Rank the Phi 4 Mini Instruct Mlx Fp16 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 Phi 4 Mini Instruct Mlx Fp16

Best Alternatives	Context / RAM	Downloads	Likes
...4 Mini Instruct Chat Mlx 16bit	128K / 7.7 GB	320	1
Ph3 Q8	128K / 4 GB	9	0
Phi 4 Mini Instruct Mlx 4Bit	128K / 2.2 GB	365	1
Phi 4 Mini Instruct Mlx 6Bit	128K / 3.1 GB	126	1
Phi 4 Mini Instruct Mlx 8Bit	128K / 4.1 GB	287	1
...hi 3 Mini 4K Instruct Sft 4bit	4K / 2.3 GB	10	0
...hi 3 Mini 4K Instruct Sft 8bit	4K / 4.1 GB	5	0
Phi 4 Mini Instruct	128K / 7.7 GB	514603	791
Phi 3.5 Mini Instruct	128K / 7.7 GB	1164079	999
Phi 3 Mini 128K Instruct	128K / 7.7 GB	233663	1700

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Phi-4-mini-instruct-mlx-fp16.