qwen3-coder-30b-a3b-instruct-mlx

qwen3_moe · 30B · 4bit

MacBook Pro (Apple M1 Pro)

32 GB · macOS 15.6.1

Tested on October 20, 2026

Top 18% Compare

Global Score

87 /100

Excellent

Hardware Fit

85/100

Quality

88/100

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 Pro
CPU: Apple M1 Pro
Cores: 10 total (8 perf + 2 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M1 Pro
OS: macOS 15.6.1
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 45.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 17 ms
Time to first token How fast the model starts responding — lower is better: 390 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: 22.4 GB (70%)
Total tokens Total number of tokens generated across all benchmark prompts: 1162

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

15/30

Quality

Reasoning

15/20

Coding

19/20

Instruction following

17/20

Structured output

15/15

Math

12/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio
Model format: MLX
Hardware profile: BALANCED
Result hash: 1fa8c8786cd40ddbf5fd7957dc5e321db491e1b95d7812db9846355a8133f487

Interpretation

Hardware fit: 85/100. Overall suitability: EXCELLENT (Global 87/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.

Bench Environment

Power: AC CPU load: avg 34% (peak 47%)

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