qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

qwen3_moe · 30B · MXFP4

THINKING MODEL

Mac Studio (Apple M2 Max)

96 GB · macOS 26.1

Tested on April 20, 2026 · Submitted by Frank

Top 0% Compare

Global Score

97 /100

Excellent

Hardware Fit

95/100

Quality

98/100

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 Studio
CPU: Apple M2 Max
Cores: 12 total (8 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 96 GB LPDDR5
GPU: Apple M2 Max
OS: macOS 26.1
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 79.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 11 ms
Time to first token How fast the model starts responding — lower is better: 1.7 s
Load time Time to load the model into memory before inference: 7.1 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.0 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 1551
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~415

Score breakdown

Speed

50/50

Time to first token

15/20

Memory

30/30

Quality

Reasoning

19/20

Coding

19/20

Instruction following

20/20

Structured output

15/15

Math

15/15

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 0.4.10+1
Model format: MLX
Hardware profile: HIGH-END
Result hash: cba6db08f94a2761a67facc00c33a5637165fd582d8a80b10e0f9b6a4008264f

Interpretation

Hardware fit: 95/100. Overall suitability: EXCELLENT (Global 97/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 13% (peak 16%)

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