gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
89 vs 71
Hardware Fit
88 vs 99
Quality Score
89 vs 59
Hardware
gemma4:12b ministral-3:3b
MachineMacBook ProMacBook Air
CPUApple M2 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b ministral-3:3b
Tokens/sec18.442.2
First chunk758 ms189 ms
TTFT758 ms189 ms
Load time0.3 s1.2 s
Memory usage7.5 GB7.0 GB
Memory %47%22%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
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
ministral-3:3b
Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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