llama3.2:3b

llama · 3.2B · Q4_K_M

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 44% Compare

Global Score

69 /100

Good

Hardware Fit

98/100

Quality

49/100

Get this model

🦙

Ollama

ollama pull llama3.2:3b

View on Ollama Library

ollama.com/library/llama3.2

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64

Performance

Tokens/sec Tokens generated per second — higher is better: 27.8
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.6
Time to first token How fast the model starts responding — lower is better: 285 ms
Load time Time to load the model into memory before inference: 1.9 s
Memory usage RAM consumed during inference — percentage of total system memory: 7.0 GB (22%)
Total tokens Total number of tokens generated across all benchmark prompts: 1112

Score breakdown

Speed

38/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

11/20

Coding

0/20

Instruction following

14/20

Structured output

12/15

Math

3/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.1.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: cb1e194cd0f396cc11e325a0f33411efbf8283dd6a339784f5eaa6b7142cd944

Interpretation

Hardware fit: 98/100. Overall suitability: GOOD (Global 69/100). Category profile: Reasoning: Adequate, Coding: Poor, Instruction Following: Adequate, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running