qwen3.5:2b

qwen35 · 2.3B · Q8_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 2, 2026

Top 14% Compare

Global Score

77 /100

Good

Hardware Fit

100/100

Quality

62/100

Get this model

🦙

Ollama

ollama pull qwen3.5:2b

View on Ollama Library

ollama.com/library/qwen3.5

🤗

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: 30.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
Time to first token How fast the model starts responding — lower is better: 215 ms
Load time Time to load the model into memory before inference: 1.8 s
Memory usage RAM consumed during inference — percentage of total system memory: 4.5 GB (14%)
Total tokens Total number of tokens generated across all benchmark prompts: 1021

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

12/20

Coding

10/20

Instruction following

13/20

Structured output

14/15

Math

4/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.5
Model format: GGUF
Hardware profile: BALANCED
Result hash: 349efe1d8c8330e6fd8541bdae845fbb0c17445c72090862165fbdf4386cedee

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 77/100). Category profile: Reasoning: Adequate, Coding: Weak, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running