lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
60 vs 89
Hardware Fit
80 vs 95
Quality Score
52 vs 87
Hardware
lfm2.5-thinking:1.2b gemma4:26b
MachineMacBook ProAZW GTR Pro
CPUApple M4 ProAMD RYZEN AI MAX+ 395
Cores1432
RAM48 GB125 GB
GPUApple M4 ProRadeon 8060S
OSmacOS 26.4.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
lfm2.5-thinking:1.2b gemma4:26b
Tokens/sec227.048.3
First chunk60 ms346 ms
TTFT30.0 s346 ms
Load time0.7 s4.4 s
Memory usage2.6 GB36.1 GB
Memory %6%29%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
gemma4:26b
Speed
45/50
TTFT
20/20
Memory
30/30
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
gemma4:26b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
14/15
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