v2.2 · 2026-06-12

Meta Llama 3.2 3B Instruct

llama-3-2-3b-instruct

TEXT-CHAT

Meta Llama 3.2 3B Instruct is a 3B 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

Meta

FAMILY

llama

MODEL TYPE

text-chat

PARAMETERS

MODALITIES

text

ARCHITECTURE

decoder-only Transformer (LlamaForCausalLM)

CONTEXT WINDOW

128,000 tokens

TRAINING TOKENS

—

RELEASE DATE

2024-09-25

LICENSE & LINKS

Llama 3.2 Community Licenselicense text

MODEL CARD

huggingface.co/meta-llama/Llama-3.2-3B-Instruct

HUGGING FACE

meta-llama/Llama-3.2-3B-Instruct

GGUF REPOSITORIES

bartowski/Llama-3.2-3B-Instruct-GGUF community conversion

Community GGUF conversion with Q4_K_M, Q5_K_M and Q8_0 file-size table.

SETUP HINTS

OLLAMA

ollama run llama3.2:3b

LM STUDIO

Use bartowski/Llama-3.2-3B-Instruct-GGUF and select Q4_K_M or Q5_K_M.

LLAMA.CPP

llama-server -hf bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M

QUANTIZATION FILE SIZES (GGUF)

Q4_K_M

2.02 GB

Q5_K_M

2.32 GB

Q8_0

3.42 GB

Quantization note: Q4_K_M

RAM / VRAM ESTIMATES

MIN RAM

4 GB

COMFORTABLE RAM

8 GB

MIN VRAM

3 GB

COMFORTABLE VRAM

4 GB

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

HARDWARE FIT

CPU only (no GPU)

yes

8 GB RAM

comfortable

16 GB RAM

comfortable

32 GB RAM

comfortable

8 GB VRAM

comfortable

12 GB VRAM

comfortable

24 GB VRAM

comfortable

Apple Silicon (unified memory)

comfortable

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 assistant deployments

·summarization and prompt rewriting

·tool-use experiments on low-memory systems

·edge-friendly multilingual chat

AVOID IF

·you need 7B-or-larger answer quality

·you need robust complex reasoning

·you need an Apache-2.0 license

CAVEATS

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

·Training-token count was not confirmed in cited sources from the fetched sources.

SOURCE URLS