gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
microllm-50m:latest
OLLAMA GGUFllama · 49.31M · F16
Jun 28, 2026 · Apple M4 Pro
Global Score
89 vs 28
Hardware Fit
88 vs 80
Quality Score
89 vs 5
Hardware
gemma4:12b microllm-50m:latest
MachineMacBook ProMac mini
CPUApple M2 ProApple M4 Pro
Cores1012
RAM16 GB24 GB
GPUApple M2 ProApple M4 Pro
OSmacOS 26.5macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b microllm-50m:latest
Tokens/sec18.41000000.0
First chunk758 ms50 ms
TTFT758 ms30.0 s
Load time0.3 s0.3 s
Memory usage7.5 GB0.1 GB
Memory %47%1%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
microllm-50m:latest
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
microllm-50m:latest
Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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