qwen3:8b

qwen3 · 8.2B · Q4_K_M

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 96% Compare

Global Score

42 /100

Marginal

Hardware Fit

60/100

Quality

30/100

Get this model

🦙

Ollama

ollama pull qwen3:8b

View on Ollama Library

ollama.com/library/qwen3

🤗

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

Performance

Tokens/sec Tokens generated per second — higher is better: 18.2
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: 12.4 s
Load time Time to load the model into memory before inference: 2.7 s
Memory usage RAM consumed during inference — percentage of total system memory: 9.5 GB (30%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429

Score breakdown

Speed

27/40

Time to first token

3/30

Memory

30/30

Quality

Reasoning

9/20

Coding

0/20

Instruction following

5/20

Structured output

4/15

Math

3/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.1.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 15bf457c99040ba6809eb62eef615654d2e75f7164e4e05fdbfa8961d7aedee6

Interpretation

Hardware fit: 60/100. Overall suitability: MARGINAL (Global 42/100). Category profile: Reasoning: Weak, Coding: Poor, Instruction Following: Weak, Structured Output: Weak, Math: Poor, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running