phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
59 vs 86
Hardware Fit
100 vs 78
Quality Score
41 vs 89
Hardware
phi:2.7b 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
phi:2.7b Kimi-48B:48B
Tokens/sec56.622.8
First chunkN/A721 ms
TTFT110 ms721 ms
Load time0.4 s23.0 s
Memory usage2.2 GB25.5 GB
Memory %7%40%
HW Fit Score Breakdown
phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
phi:2.7b
Reasoning
7/20
Coding
4/20
Instruction
9/20
Structured
11/15
Math
8/15
Multilingual
2/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Adequate 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