lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
Global Score
60 vs 76
Hardware Fit
80 vs 82
Quality Score
52 vs 73
Hardware
lfm2.5-thinking:1.2b gemma4:e2b
MachineMacBook ProLENOVO 20U30029MB
CPUApple M4 ProIntel Core™ i5-10210U
Cores148
RAM48 GB15 GB
GPUApple M4 ProCometLake-U GT2 [UHD Graphics]
OSmacOS 26.4.1Pop 24.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
lfm2.5-thinking:1.2b gemma4:e2b
Tokens/sec227.013.5
First chunk60 ms1270 ms
TTFT30.0 s1.3 s
Load time0.7 s13.4 s
Memory usage2.6 GB6.5 GB
Memory %6%42%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
gemma4:e2b
Speed
35/50
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
gemma4:e2b
Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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