lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
60 vs 86
Hardware Fit
80 vs 78
Quality Score
52 vs 89
Hardware
lfm2.5-thinking:1.2b Kimi-48B:48B
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M4 ProIntel Core™ Ultra X7 358H
Cores1416
RAM48 GB64 GB
GPUApple M4 ProIntel(R) Arc(TM) B390 GPU
OSmacOS 26.4.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b Kimi-48B:48B
Tokens/sec227.022.8
First chunk60 ms721 ms
TTFT30.0 s721 ms
Load time0.7 s23.0 s
Memory usage2.6 GB25.5 GB
Memory %6%40%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
lfm2.5-thinking:1.2b
Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak 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