qwen2.5-math-1.5b-instruct

qwen2 · 1.5B · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 4, 2026

Top 87% Compare

Global Score

45 /100

Marginal

Hardware Fit

99/100

Quality

22/100

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: 91.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±3.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 205 ms
Time to first token How fast the model starts responding — lower is better: 205 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: 0.8 GB (3%)
Total tokens Total number of tokens generated across all benchmark prompts: 1656

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

29/30

Quality

Reasoning

2/20

Coding

0/20

Instruction following

3/20

Structured output

1/15

Math

14/15

Multilingual

2/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: 77452349b7cdbe98b4bd681016ca69728c7707b4182b2c7ff778a5a6b1715834

Interpretation

Hardware fit: 99/100. Overall suitability: MARGINAL (Global 45/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Strong, Multilingual: Poor.

Bench Environment

Power: AC CPU load: avg 21% (peak 25%)

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