Back to leaderboard

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
84 vs 78
Hardware Fit
82 vs 54
Quality Score
85 vs 88

Hardware

gemma4:12b-mlx qwen3-coder:30b-a3…
MachineMacBook ProHP HP Pavilion Laptop 15-eh1xxx
CPUApple M2 ProAMD Ryzen 5 5500U
Cores1012
RAM16 GB63 GB
GPUApple M2 ProAMD Radeon(TM) Graphics
OSmacOS 26.5Microsoft Windows 10 Enterprise LTSC 10.0.19044
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:12b-mlx qwen3-coder:30b-a3…
Tokens/sec27.28.0
First chunk732 ms1468 ms
TTFT8.1 s1.5 s
Load time3.5 s114.5 s
Memory usage7.1 GB33.5 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
11/50
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
16/20
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest