qwen/qwen3-8b

qwen3 · 8B · 4bit

THINKING MODEL

Mac mini (Apple M4 Pro)

64 GB · macOS 15.7.4

Tested on March 5, 2026

Top 5% Compare

Global Score

89 /100

Excellent

Hardware Fit

95/100

Quality

87/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Mac mini
CPU: Apple M4 Pro
Cores: 14 total (10 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 64 GB LPDDR5
GPU: Apple M4 Pro
OS: macOS 15.7.4
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 33.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±16.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 257 ms
Time to first token How fast the model starts responding — lower is better: 257 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: 4.3 GB (7%)
Total tokens Total number of tokens generated across all benchmark prompts: 1104

Score breakdown

Speed

45/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

19/20

Coding

14/20

Instruction following

16/20

Structured output

15/15

Math

13/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: HIGH-END
Result hash: 15af8284c31d100193e89ef375c3a251f4320c9cddb89c7d5bb3864e7e65a6f4

Interpretation

Hardware fit: 95/100. Overall suitability: EXCELLENT (Global 89/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Token speed is unstable (stddev 16.7 tok/s, mean 33.4 tok/s) — may indicate thermal throttling or memory pressure.

Bench Environment

Power: AC CPU load: avg 24% (peak 26%)

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