qwen2.5:0.5b

qwen2 · 494.03M · Q4_K_M

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 80% Compare

Global Score

59 /100

Marginal

Hardware Fit

99/100

Quality

33/100

Get this model

🦙

Ollama

ollama pull qwen2.5:0.5b

View on Ollama Library

ollama.com/library/qwen2.5

🤗

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: 162.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.8
Time to first token How fast the model starts responding — lower is better: 81 ms
Load time Time to load the model into memory before inference: 0.5 s
Memory usage RAM consumed during inference — percentage of total system memory: 1.7 GB (5%)
Total tokens Total number of tokens generated across all benchmark prompts: 1255

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

29/30

Quality

Reasoning

6/20

Coding

0/20

Instruction following

7/20

Structured output

11/15

Math

5/15

Multilingual

4/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 25c5e9a65241ea1dfd0d469fe7617f3003ddaff5b5fb5903094d158b7c863bd8

Interpretation

Hardware fit: 99/100. Overall suitability: MARGINAL (Global 59/100). Category profile: Reasoning: Weak, Coding: Poor, Instruction Following: Weak, Structured Output: Adequate, Math: Weak, Multilingual: Weak.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running