laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
Global Score
84 vs 76
Hardware Fit
100 vs 100
Quality Score
77 vs 65
Hardware
laguna-xs-2.1 llama3.2:latest
MachineAZW GTR ProMicro-Star International Co., Ltd. MS-7B79
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 5 2600X Six-Core Processor
Cores3212
RAM125 GB16 GB
GPURadeon 8060SNVIDIA GeForce GTX 1080
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
laguna-xs-2.1 llama3.2:latest
Tokens/sec65.957.0
First chunk281 ms264 ms
TTFT281 ms264 ms
Load time9.9 s9.7 s
Memory usage30.1 GB2.6 GB
Memory %24%16%
HW Fit Score Breakdown
laguna-xs-2.1
Speed
50/50
TTFT
20/20
Memory
30/30
llama3.2:latest
Speed
50/50
TTFT
20/20
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
llama3.2:latest
Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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