llama-3.2-3b-instruct

llama · 3B · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 3, 2026

Top 35% Compare

Global Score

72 /100

Good

Hardware Fit

100/100

Quality

60/100

Get this model

🦙

Ollama

ollama pull llama-3.2-3b-instruct

View on Ollama Library

ollama.com/library/llama-3.2-3b-instruct

🤗

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
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 48.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.8
Time to first token How fast the model starts responding — lower is better: 265 ms
Load time Time to load the model into memory before inference: 0.0 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.0 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 1148

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

9/20

Coding

13/20

Instruction following

14/20

Structured output

13/15

Math

3/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Lm-studio unknown
Model format: GGUF
Hardware profile: BALANCED
Result hash: eb7011bf47c90b7495a3de535130fb87dba7e00fdb4bbbd45efde1e0065867f0

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 72/100). Category profile: Reasoning: Weak, Coding: Adequate, Instruction Following: Adequate, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running