mlx-community/Llama-3.2-1B-Instruct-4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 5, 2026

Top 72% Compare

Global Score

57 /100

Marginal

Hardware Fit

100/100

Quality

39/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

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: 126.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±3.9
First chunk latency Delay before the first streamed chunk arrives from runtime: 139 ms
Time to first token How fast the model starts responding — lower is better: 139 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 0.3 GB (1%)
Total tokens Total number of tokens generated across all benchmark prompts: 1285

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

5/20

Coding

3/20

Instruction following

15/20

Structured output

10/15

Math

1/15

Multilingual

5/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: GGUF
Hardware profile: BALANCED
Result hash: 5d75a4a87700131e4bb60e4b9a84e99721c7c0711dee2340392e7c9ad47f2e85

Interpretation

Hardware fit: 100/100. Overall suitability: MARGINAL (Global 57/100). Category profile: Reasoning: Weak, Coding: Poor, Instruction Following: Strong, Structured Output: Adequate, Math: Poor, Multilingual: Adequate.

Bench Environment

Power: AC CPU load: avg 17% (peak 19%)

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