laguna-xs-2.1

ECO MODE

AZW GTR Pro (AMD RYZEN AI MAX+ 395)

125 GB · Ubuntu 24.04.4 LTS

Tested on August 1, 2026

Top 21% Compare

Global Score

84 /100

Excellent

Hardware Fit

100/100

Quality

77/100

Get this model

🦙

Ollama

ollama pull laguna-xs-2.1

View on Ollama Library

ollama.com/library/laguna-xs-2.1

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: AZW GTR Pro
CPU: AMD RYZEN AI MAX+ 395
Cores: 32 threads (16 cores)
Frequency: 3 GHz
RAM: 125 GB
GPU: Radeon 8060S
OS: Ubuntu 24.04.4 LTS
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 65.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 281 ms
Time to first token How fast the model starts responding — lower is better: 281 ms
Load time Time to load the model into memory before inference: 9.9 s
Memory usage RAM consumed during inference — percentage of total system memory: 30.1 GB (24%)
Total tokens Total number of tokens generated across all benchmark prompts: 1283

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

8/20

Coding

18/20

Instruction following

16/20

Structured output

14/15

Math

11/15

Multilingual

10/10

Category levels

Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.5
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 236c1ffe273d707de453c35907400811a92714a8e5cb681c299703149eadc1a9

Interpretation

Hardware fit: 100/100. Overall suitability: EXCELLENT (Global 84/100). Category profile: Reasoning: Weak, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Adequate, Multilingual: Strong.

Warnings

System was in low-power mode during this benchmark.
CPU appears throttled (2.2 GHz current vs 3.0 GHz nominal, 73%).
Significant swap activity during benchmark (+0.9 GB). Model may exceed available RAM — results are severely degraded.

Bench Environment

Thermal: nominal Swap delta: +0.9 GB CPU load: avg 5% (peak 6%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest