mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
45 vs 86
Hardware Fit
100 vs 78
Quality Score
21 vs 89
Hardware
mlx-community/quan… Kimi-48B:48B
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
mlx-community/quan… Kimi-48B:48B
Tokens/sec44.422.8
First chunk336 ms721 ms
TTFT336 ms721 ms
Load timeN/A23.0 s
Memory usage0.1 GB25.5 GB
Memory %0%40%
HW Fit Score Breakdown
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
mlx-community/quantized…
Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor
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