gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jun 26, 2026 · Cortex-X925
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
86 vs 80
Hardware Fit
78 vs 95
Quality Score
90 vs 73
Hardware
gemma4:12b lfm2.5:8b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
gemma4:12b lfm2.5:8b
Tokens/sec26.398.5
First chunk545 ms167 ms
TTFT545 ms2.5 s
Load time9.5 s3.0 s
Memory usage8.4 GB6.0 GB
Memory %7%37%
HW Fit Score Breakdown
gemma4:12b
Speed
28/50
TTFT
20/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
Quality
gemma4:12b
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate 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