gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
63 vs 89
Hardware Fit
62 vs 95
Quality Score
63 vs 87
Hardware
gemma4:12b gemma4:26b
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:12b gemma4:26b
Tokens/sec15.348.3
First chunk1142 ms346 ms
TTFT30.0 s346 ms
Load time5.4 s4.4 s
Memory usage7.6 GB36.1 GB
Memory %47%29%
HW Fit Score Breakdown
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
gemma4:26b
Speed
45/50
TTFT
20/20
Memory
30/30
Quality
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:26b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
14/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong 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