laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
84 vs 88
Hardware Fit
100 vs 86
Quality Score
77 vs 89
Hardware
laguna-xs-2.1 gemma4:12b-it-qat
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3212
RAM125 GB24 GB
GPURadeon 8060SApple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.6.1
Archx64arm64
Power Modelow-powerbalanced
Performance
laguna-xs-2.1 gemma4:12b-it-qat
Tokens/sec65.930.0
First chunk281 ms686 ms
TTFT281 ms7.1 s
Load time9.9 s5.4 s
Memory usage30.1 GB7.1 GB
Memory %24%30%
HW Fit Score Breakdown
laguna-xs-2.1
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
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
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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