gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
qwen3-coder:30b-a3b-q8_0
OLLAMA GGUFqwen3moe · 30.5B · Q8_0
Jun 18, 2026 · Intel Core™ Ultra 9 285HX
Global Score
84 vs 90
Hardware Fit
82 vs 89
Quality Score
85 vs 90
Hardware
gemma4:12b-mlx qwen3-coder:30b-a3…
MachineMacBook ProMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJG
CPUApple M2 ProIntel Core™ Ultra 9 285HX
Cores1024
RAM16 GB63 GB
GPUApple M2 ProIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPU
OSmacOS 26.5Microsoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx qwen3-coder:30b-a3…
Tokens/sec27.243.1
First chunk732 ms957 ms
TTFT8.1 s957 ms
Load time3.5 s52.0 s
Memory usage7.1 GB33.6 GB
Memory %44%53%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
qwen3-coder:30b-a3b-q8_0
Speed
46/50
TTFT
19/20
Memory
24/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:30b-a3b-q8_0
Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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