gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
maternion/ling-3.0-tiny:8b
OLLAMA GGUFbailingmoe3 · 7.9B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
89 vs 68
Hardware Fit
88 vs 98
Quality Score
89 vs 55
Hardware
gemma4:12b maternion/ling-3.0…
MachineMacBook ProMacBook Pro
CPUApple M2 ProApple M1 Pro
Cores1010
RAM16 GB16 GB
GPUApple M2 ProApple M1 Pro
OSmacOS 26.5macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b maternion/ling-3.0…
Tokens/sec18.573.6
First chunk752 ms190 ms
TTFT752 ms190 ms
Load time6.1 s2.9 s
Memory usage7.5 GB5.9 GB
Memory %47%37%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
maternion/ling-3.0-tiny…
Speed
50/50
TTFT
20/20
Memory
28/30
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
maternion/ling-3.0-tiny…
Reasoning
19/20
Coding
17/20
Instruction
3/20
Structured
0/15
Math
15/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Poor Math: Strong 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