v2.2 · 2026-06-12

Phi-3 Mini 3.8B Instruct

phi-3-mini-4k-instruct

TEXT-CHAT

Phi-3 Mini 3.8B Instruct is a 3.8B text chat model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER

Microsoft

FAMILY

Phi-3

MODEL TYPE

text-chat

PARAMETERS

3.8B

MODALITIES

text

ARCHITECTURE

dense decoder-only Transformer

CONTEXT WINDOW

4,096 tokens

TRAINING TOKENS

4.9T

RELEASE DATE

2024-04-23

LICENSE & LINKS

MITlicense text

MODEL CARD

huggingface.co/microsoft/Phi-3-mini-4k-instruct

HUGGING FACE

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

GGUF REPOSITORIES

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

Official Microsoft GGUF repository for the 4K instruct checkpoint.

tensorblock/Phi-3-mini-4k-instruct-GGUF community conversion

Community GGUF repository used for Q5_K_M and Q8_0 file-size evidence not present in the official GGUF repo listing.

SETUP HINTS

OLLAMA

Use ollama run phi3:mini for the local Mini tag; verify the exact context variant because Ollama also exposes 128K Phi-3 tags.

LM STUDIO

Search for microsoft/Phi-3-mini-4k-instruct-gguf or tensorblock/Phi-3-mini-4k-instruct-GGUF and select Q4_K_M.

LLAMA.CPP

Use the Microsoft official GGUF when possible; use the TensorBlock community GGUF only when a specific K-quant file is needed.

QUANTIZATION FILE SIZES (GGUF)

Q4_K_M

2.393 GB

Q5_K_M

2.815 GB

Q8_0

4.061 GB

Quantization note: Q4_K_M for default local use; Q5_K_M if it still fits comfortably in RAM/VRAM.

RAM / VRAM ESTIMATES

MIN RAM

5 GB

COMFORTABLE RAM

8 GB

MIN VRAM

4 GB

COMFORTABLE VRAM

6 GB

These are conservative local-inference estimates, not official hardware requirements.

HARDWARE FIT

CPU only (no GPU)

yes

8 GB RAM

yes

16 GB RAM

yes

32 GB RAM

yes

8 GB VRAM

yes

12 GB VRAM

yes

24 GB VRAM

yes

Apple Silicon (unified memory)

yes

Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.

BEST FOR

·small local chat

·math and logic prompts

·latency-sensitive local assistants

·laptop inference

AVOID IF

·a context window above 4K is required for the selected checkpoint

·multimodal input is required

·broad multilingual support is required

CAVEATS

·This record uses the official Microsoft 4K instruct checkpoint because it has an official Microsoft GGUF repository; Phi-3 Mini also has a 128K variant.

·The current Microsoft Hugging Face card describes a June 2024 updated checkpoint with 4.9T training tokens, while earlier official launch/GGUF material described the original release with 3.3T tokens.

·Ollama's current Phi-3 page mixes Mini tags and 128K tags; verify the selected tag before relying on context length.

·RAM and VRAM figures are estimates based on GGUF file size plus conservative runtime and KV-cache overhead, not official hardware requirements.

SOURCE URLS