Skip to content
localllm
日本語

microsoft

Phi-3-mini-4k-instruct

Parameters
3.8B
Max context length
4,096
Architecture
phi3
License
Commercial OK
License
mit

About Phi-3-mini-4k-instruct

Phi-3-mini-4k-instruct is a model published in GGUF format. GGUF files are published by microsoft/Phi-3-mini-4k-instruct-gguf. It has about 3.8B parameters, the phi3 architecture, a maximum context length of 4,096 tokens (values written in the GGUF).

There is one quantization, F16, with a file size of 7.64 GB (actual size on Hugging Face).

According to microsoft/Phi-3-mini-4k-instruct-gguf, the license is MIT License, which allows commercial use (keep the license text and copyright notice when redistributing). Check the original license for the terms of use.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

microsoft/Phi-3-mini-4k-instruct-gguf

Published by the original developer About this label

Last checked: Oct 22, 2026

Architecture
phi3
Supported before llama.cpp b4409
Parameters
3.8B
Max context length
4,096
License
mit Commercial OK
File size and memory per quantization for Phi-3-mini-4k-instruct (microsoft/Phi-3-mini-4k-instruct-gguf)
Quantization File size Measured Quality guide 4,096 max
F16 7.64 GB Original precision 10.3 GB 
Ollama  ollama run hf.co/microsoft/Phi-3-mini-4k-instruct-gguf:F16
llama.cpp  llama-server -hf microsoft/Phi-3-mini-4k-instruct-gguf:F16

Third-party evaluations

Values from other organizations for the original model before quantization. Not this site's own rating. Values are for the original model before quantization. GGUF quantization (especially small quantizations) can lower performance.

Human preference (LMArena)

1,128 1,122–1,135

Phi-3 Mini 4K Instruct · 20,118 votes · Values as of Nov 9, 2026

Source: LMArena (CC BY 4.0). Original leaderboard · See in ranking

License and commercial use

MIT License Commercial OK

Allows commercial use, modification and redistribution. When redistributing, keep the copyright notice and license text.

The original model's license has not been fetched yet, so this is based on the GGUF repository's label. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Example commands using F16. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/microsoft/Phi-3-mini-4k-instruct-gguf:F16

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf microsoft/Phi-3-mini-4k-instruct-gguf:F16

LM Studio

Paste microsoft/Phi-3-mini-4k-instruct-gguf into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run Phi-3-mini-4k-instruct (F16)?
The file size is 7.64 GB (measured). With a 4,096-token context, the estimated memory including the KV cache is 10.3 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can Phi-3-mini-4k-instruct be used commercially?
The license is MIT License (Commercial use allowed).Allows commercial use, modification and redistribution. When redistributing, keep the copyright notice and license text. Check the original license text before deciding.
What is the command to run Phi-3-mini-4k-instruct with Ollama?
Run "ollama run hf.co/microsoft/Phi-3-mini-4k-instruct-gguf:F16" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.