laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
phi3:14b
OLLAMA GGUFphi3 · 14.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
84 vs 63
Hardware Fit
100 vs 83
Quality Score
77 vs 55
Hardware
laguna-xs-2.1 phi3:14b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
laguna-xs-2.1 phi3:14b
Tokens/sec65.912.7
First chunk281 msN/A
TTFT281 ms434 ms
Load time9.9 s0.9 s
Memory usage30.1 GB17.7 GB
Memory %24%55%
HW Fit Score Breakdown
laguna-xs-2.1
Speed
50/50
TTFT
20/20
Memory
30/30
phi3:14b
Speed
23/50
TTFT
30/20
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
phi3:14b
Reasoning
14/20
Coding
2/20
Instruction
14/20
Structured
7/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Weak 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