gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
83 vs 80
Hardware Fit
60 vs 95
Quality Score
93 vs 73
Hardware
gemma4:31b lfm2.5:8b
MachineASUSTeK COMPUTER INC. GX10MacBook 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
gemma4:31b lfm2.5:8b
Tokens/sec10.998.5
First chunk681 ms167 ms
TTFT681 ms2.5 s
Load time16.6 s3.0 s
Memory usage21.4 GB6.0 GB
Memory %18%37%
HW Fit Score Breakdown
gemma4:31b
Speed
10/50
TTFT
20/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
Quality
gemma4:31b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
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