gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
63 vs 84
Hardware Fit
62 vs 100
Quality Score
63 vs 77
Hardware
gemma4:12b laguna-xs-2.1
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 Modebalancedlow-power
Performance
gemma4:12b laguna-xs-2.1
Tokens/sec15.365.9
First chunk1142 ms281 ms
TTFT30.0 s281 ms
Load time5.4 s9.9 s
Memory usage7.6 GB30.1 GB
Memory %47%24%
HW Fit Score Breakdown
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
laguna-xs-2.1
Speed
50/50
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
laguna-xs-2.1
Reasoning
8/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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