gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
91 vs 86
Hardware Fit
96 vs 78
Quality Score
89 vs 89
Hardware
gemma4:12b-mlx Kimi-48B:48B
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M2 ProIntel Core™ Ultra X7 358H
Cores1016
RAM16 GB64 GB
GPUApple M2 ProIntel(R) Arc(TM) B390 GPU
OSmacOS 26.5Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx Kimi-48B:48B
Tokens/sec24.722.8
First chunk610 ms721 ms
TTFT610 ms721 ms
Load time3.6 s23.0 s
Memory usage7.1 GB25.5 GB
Memory %45%40%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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