qwen2.5-coder-3b-instruct-mlx

qwen2 · 3B · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 4, 2026

Top 36% Compare

Global Score

73 /100

Good

Hardware Fit

100/100

Quality

61/100

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: 52.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 285 ms
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: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 1.6 GB (5%)
Total tokens Total number of tokens generated across all benchmark prompts: 1127

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

7/20

Coding

14/20

Instruction following

13/20

Structured output

14/15

Math

4/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: a9020ab0c5d6ad9d400ebe13e1265cbda0df05e117c1e882255a2047b367dd83

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 73/100). Category profile: Reasoning: Weak, Coding: Adequate, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 16% (peak 20%)

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