Skip to content
Local AI Wizard
Your machine
Theme

Llama 3.2 family: which size to run

2 sizes, 1.23B–3.21B parameters · Meta

Checked

Sizes

Llama 3.2 sizes
ModelArchitecture
Llama 3.2 1B InstructMeta · Llama 3.2 · Sep 25, 20241.23BDense128,000No LiveBench result for this model in release 2026-06-25930.80.7
Llama 3.2 3B InstructMeta · Llama 3.2 · Sep 25, 20243.21BDense128,000No LiveBench result for this model in release 2026-06-2511521.8

Each size is its own model, with its own scores and memory needs. Q4 estimates are planning figures, not measurements; file sizes are published. The Mac or PC column is for a 32 GB or larger machine (8 GB reserve); machines under 32 GB reserve 25% of their memory (2 to 8 GB), so they need less. The publisher lists 1B, 3B (text in, text out).

How to read this table

Q4 means compressed to about 4 bits per weight. GGUF (llama.cpp, Ollama, LM Studio) and MLX (Apple silicon) are file formats; the sizes shown are the published 4-bit files. A dash means no value is published or collected for that size; the reason is in the cell's accessible text.

Which size fits my machine

The largest size whose Q4 planning estimate fits what each machine offers. A planning estimate, not a measurement and not a speed.

Largest Llama 3.2 size per machine
MachineLargest Llama 3.2 size with enough memory
Mac mini M2 · 8 GB unified8Llama 3.2 3B Instruct5
Mac mini M4 · 16 GB unified16Llama 3.2 3B Instruct7
Mac mini M4 · 24 GB unified24Llama 3.2 3B Instruct9
Mac mini M4 · 32 GB unified32Llama 3.2 3B Instruct11
Mac mini M5 Pro · 64 GB unified56Llama 3.2 3B Instruct11
Mac Studio M5 Max · 128 GB unified104Llama 3.2 3B Instruct11
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified392Llama 3.2 3B Instruct11
RTX 4060 · 8 GB VRAM8Llama 3.2 3B Instruct5
RTX 3060 · 12 GB VRAM12Llama 3.2 3B Instruct5
RTX 5080 · 16 GB VRAM16Llama 3.2 3B Instruct5
RTX 4090 · 24 GB VRAM24Llama 3.2 3B Instruct5
RTX 5090 · 32 GB VRAM32Llama 3.2 3B Instruct5
DGX H100 · 8 × 80 GB640Llama 3.2 3B Instruct19

A dash means no size of this family fits that machine. The requirement is the size's Q4 estimate with that machine's own reserve: a graphics card reserves 2 GB, as in the sizes table; a Mac or PC reserves 25% of its memory (2 to 8 GB), so below 32 GB its figure is lower than the sizes table's. A server profile reserves 2 GB per graphics card, so its figure is higher.

Smallest machine for each size

The profile with the least memory that still has enough for the size's Q4 estimate, from the hardware catalog.

Smallest machine per Llama 3.2 size
SizeSmallest Mac or PC-memory profileSmallest graphics-card profile
Llama 3.2 1B InstructMac mini 2020 · M1 · 8 GBGTX 1650 · 4 GB
Llama 3.2 3B InstructMac mini 2020 · M1 · 8 GBRTX 3050 · 6 GB

A dash means no profile of that kind in the catalog has enough memory for the size.

Memory by file precision

The same planning formula at three precisions (0.625, 1.125 and 2 bytes per parameter, plus working room and the system reserve). Estimates, not measurements.

Llama 3.2 memory estimate by precision
Size
Llama 3.2 1B Instruct93104115
Llama 3.2 3B Instruct1151371610

Family tree

Family, sizes and, for each size, the two 4-bit files the tables use (GGUF Q4_K_M and MLX 4-bit) when one was collected. Other precisions are not drawn here.

Llama 3.2 family: sizes and published filesSwipe sideways to see the files, or read the list below.
Llama 3.2 family: sizes and published filesFamilySizesFilesLlama 3.2Meta1B InstructGGUF Q4_K_M0.8 GBMLX 4-bit0.7 GB3B InstructGGUF Q4_K_M2 GBMLX 4-bit1.8 GB

The same tree as a list:

  • Llama 3.2 · Meta
    • 1B Instruct
      • GGUF Q4_K_M · 0.8 GB · bartowski/Llama-3.2-1B-Instruct-GGUF, read Oct 23, 2026
      • MLX 4-bit · 0.7 GB · mlx-community/Llama-3.2-1B-Instruct-4bit, read Oct 23, 2026
    • 3B Instruct
      • GGUF Q4_K_M · 2 GB · bartowski/Llama-3.2-3B-Instruct-GGUF, read Oct 23, 2026
      • MLX 4-bit · 1.8 GB · mlx-community/Llama-3.2-3B-Instruct-4bit, read Oct 23, 2026

Learn more

Sources

Where the family and its sizes are named, and where each number comes from.