Back to leaderboard

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
84 vs 81
Hardware Fit
100 vs 100
Quality Score
77 vs 73

Hardware

laguna-xs-2.1 llama-3.1-8b-instr…
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 5 5500
Cores3212
RAM125 GB31 GB
GPURadeon 8060SNavi 44 [Radeon RX 9060 XT]
OSUbuntu 24.04.4 LTSNobara Linux 43
Archx64x64
Power Modelow-powerperformance

Performance

laguna-xs-2.1 llama-3.1-8b-instr…
Tokens/sec65.935.6
First chunk281 ms52 ms
TTFT281 ms256 ms
Load time9.9 sN/A
Memory usage30.1 GB8.6 GB
Memory %24%28%

HW Fit Score Breakdown

laguna-xs-2.1

Speed
50/50
TTFT
20/20
Memory
30/30

llama-3.1-8b-instruct

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

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View laguna-xs-2.1 details | View llama-3.1-8b-instr… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest