qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Aug 20, 2026 · Apple M4 Max
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 25, 2026 · Intel Core™ Ultra X7 358H
Global Score
96 vs 68
Hardware Fit
95 vs 21
Quality Score
96 vs 88
Hardware
qwen3-30b-a3b-thin… GPT-120B:120b
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M4 MaxIntel Core™ Ultra X7 358H
Cores1616
RAM128 GB64 GB
GPUApple M4 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… GPT-120B:120b
Tokens/sec112.812.1
First chunk21 ms4392 ms
TTFT1.5 s8.7 s
Load time3.5 s80.1 s
Memory usage0.0 GB61.0 GB
Memory %0%96%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest