llama3.2:3b

llama · 3.2B · Q4_K_M

NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super (Cortex-A78AE)

7 GB · Ubuntu 22.04.5 LTS

Tested on June 25, 2026 · Submitted by Tram

Top 46% Compare

Global Score

74 /100

Good

Hardware Fit

99/100

Quality

63/100

Get this model

🦙

Ollama

ollama pull llama3.2:3b

View on Ollama Library

ollama.com/library/llama3.2

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPU: Cortex-A78AE
Cores: 6 total (6 perf)
Frequency: 1.52 GHz
RAM: 7 GB
GPU: Integrated / Unknown
OS: Ubuntu 22.04.5 LTS
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 21.1
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 1.0 s
Time to first token How fast the model starts responding — lower is better: 1.0 s
Load time Time to load the model into memory before inference: 8.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 2.4 GB (32%)
Total tokens Total number of tokens generated across all benchmark prompts: 1112

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

29/30

Quality

Reasoning

10/20

Coding

14/20

Instruction following

15/20

Structured output

12/15

Math

3/15

Multilingual

9/10

Category levels

Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.10
Model format: GGUF
Hardware profile: ENTRY
Result hash: 1dd9c19eb12116895eb6303e8abdcac7d88608f0f8c6f943d57b1c98dfaa4b2c

Interpretation

Hardware fit: 99/100. Overall suitability: GOOD (Global 74/100). Category profile: Reasoning: Adequate, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Warnings

CPU appears throttled (1.1 GHz current vs 1.5 GHz nominal, 75%).

Bench Environment

Thermal: nominal Swap delta: +0.0 GB CPU load: avg 6% (peak 10%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest