HomeModel Memory Fit › Llama 3.2 3B Instruct
Model Memory Fit · LLM

Llama 3.2 3B Instruct: memory fit on every Jetson module.

Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026

3.21 B parameters · 28 layers · 131,072-token max context. Hugging Face: meta-llama/Llama-3.2-3B-Instruct.

Model facts

FactValueNote
Parameters3.213 B
Layers28
Hidden size3072
Attention heads24
KV heads8
Head dimension128
Max context131,072 tokens
dtypebfloat16
Vocabulary128,256

Hugging Face (mirror: unsloth/Llama-3.2-3B-Instruct) · hf:unsloth/Llama-3.2-3B-Instruct · config.json · verified 2026-09-07

“"num_hidden_layers": 28, "hidden_size": 3072, "head_dim": 128”

Parameters source

  • Hugging Face (mirror: unsloth/Llama-3.2-3B-Instruct) · hf:unsloth/Llama-3.2-3B-Instruct · verified 2026-09-07 · model.safetensors.index.json · class A
    “"total_size": 6425499648”

Published quantised artefacts

A file the publisher or a community mirror actually ships, used as the class-A weight figure when the requested quant matches. Any quant without a row here falls back to parameters × bytes-per-parameter (class D for block quants).

QuantFormatFileSizeSource
GGUF Q4_K_M / INT4 (AWQ, MLC q4f16)GGUF Q4_K_MLlama-3.2-3B-Instruct-Q4_K_M.gguf2.019 GBbartowski (community GGUF) · hf:bartowski/Llama-3.2-3B-Instruct-GGUF · verified 2026-09-07
INT8 / GGUF Q8_0GGUF Q8_0Llama-3.2-3B-Instruct-Q8_0.gguf3.422 GBbartowski (community GGUF) · hf:bartowski/Llama-3.2-3B-Instruct-GGUF · verified 2026-09-07

Jetson tokens/s measurements

Published or archived throughput numbers, not modelled. Class C (external measured benchmark).

ModuleRuntimeQuantMeasuredSource
Jetson Orin Nano 8GBMLCINT4 (q4f16_ft)27.7 tok/sNVIDIA Jetson AI Lab (archive) · jetson-ai-lab:tutorial_slm.html · verified 2026-09-07
Jetson AGX Orin 64GBMLCINT4 (q4f16_ft)80.4 tok/sNVIDIA Jetson AI Lab (archive) · jetson-ai-lab:tutorial_slm.html · verified 2026-09-07
Jetson Orin Nano Superunspecified (archived benchmark)43.07 tok/sNVIDIA Jetson AI Lab (archive) · jetson-ai-lab:benchmarks.html · verified 2026-09-07

Every module × every quantisation

Verdict and total memory at 4096-token context, 1 sequence, llama.cpp, headless. Q4 cells link to the static breakdown page; every other cell links to the live engine at that quantisation.

Notes

meta-llama org repo returns 401 (gated); unsloth mirror (byte-identical weights) used.

Method and data: Model Memory Fit methodology. Full registry: model-memory.json.

Change the context, concurrency or runtime.

The live engine covers any context length, sequence count, KV precision and runtime, with a permanent link.

OPEN MODEL MEMORY FIT →