What are the hardware requirements for Phi 4 Pruned?

Phi 4 Pruned requires approximately 24 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 Pruned and how large is it?

Phi 4 Pruned is developed by exp-models, a model with 11.9b 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 Pruned?

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

Phi 4 Pruned by exp-models — VRAM 24GB, 16K context

Name: Phi 4 Pruned
Author: exp-models

Phi 4 Pruned is an open-source language model by exp-models. Features: 11.9b LLM, VRAM: 24GB, Context: 16K, Merged, LLM Explorer Score: 0.16.

Merged Model Base model:finetune:unsloth/ph... Base model:unsloth/phi-4 Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/exp-models/phi-4-pruned

Phi 4 Pruned Parameters and Internals

LLM Name	Phi 4 Pruned
Repository 🤗	https://huggingface.co/exp-models/phi-4-pruned
Base Model(s)	Phi 4 unsloth/phi-4
Merged Model	Yes
Model Size	11.9b
Required VRAM	24 GB
Updated	2026-08-04
Maintainer	exp-models
Model Type	llama
Model Files	5.0 GB: 1-of-5 5.0 GB: 2-of-5 5.0 GB: 3-of-5 4.9 GB: 4-of-5 4.1 GB: 5-of-5
Model Architecture	LlamaForCausalLM
Context Length	16384
Model Max Length	16384
Transformers Version	4.48.2
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|dummy_87\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the Phi 4 Pruned 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 Pruned

Best Alternatives	Context / RAM	Downloads	Likes
Phi Lthy4	16K / 23.9 GB	33	61

Note: green Score (e.g. "73.2") means that the model is better than exp-models/phi-4-pruned.