laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
84 vs 80
Hardware Fit
100 vs 60
Quality Score
77 vs 88
Hardware
laguna-xs-2.1 qwen3-coder:30b
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i7-12700K
Cores3220
RAM125 GB96 GB
GPURadeon 8060SParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
laguna-xs-2.1 qwen3-coder:30b
Tokens/sec65.914.7
First chunk281 ms796 ms
TTFT281 ms796 ms
Load time9.9 s0.2 s
Memory usage30.1 GB17.9 GB
Memory %24%19%
HW Fit Score Breakdown
laguna-xs-2.1
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
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
qwen3-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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