Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
86 vs 78
Hardware Fit
78 vs 72
Quality Score
89 vs 81
Hardware
Kimi-48B:48B gemma4:e4b-mlx
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M2 Pro
Cores1610
RAM64 GB16 GB
GPUIntel(R) Arc(TM) B390 GPUApple M2 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B gemma4:e4b-mlx
Tokens/sec22.826.9
First chunk721 ms222 ms
TTFT721 ms222 ms
Load time23.0 s0.1 s
Memory usage25.5 GB15.4 GB
Memory %40%96%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
Quality
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
gemma4:e4b-mlx
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate 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