gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
33 vs 73
Hardware Fit
50 vs 93
Quality Score
25 vs 65
Hardware
gemma4:26b lfm2.5:latest
MachineMac miniLENOVO 20L7CTO1WW
CPUApple M4Intel Core™ i5-8350U
Cores108
RAM24 GB23 GB
GPUApple M4Kaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.3Fedora Linux 44
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:26b lfm2.5:latest
Tokens/sec20.018.3
First chunk941 ms981 ms
TTFT30.0 s981 ms
Load time0.2 s8.0 s
Memory usage20.3 GB4.9 GB
Memory %85%21%
HW Fit Score Breakdown
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
Quality
gemma4:26b
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate 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