gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
94 vs 84
Hardware Fit
91 vs 100
Quality Score
95 vs 77
Hardware
gpt-oss:20b laguna-xs-2.1
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)AZW GTR Pro
CPUAMD RYZEN AI MAX+ 395AMD RYZEN AI MAX+ 395
Cores3232
RAM64 GB125 GB
GPUAMD Radeon(TM) 8060S GraphicsRadeon 8060S
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
gpt-oss:20b laguna-xs-2.1
Tokens/sec48.065.9
First chunk357 ms281 ms
TTFT2.3 s281 ms
Load time0.2 s9.9 s
Memory usage16.4 GB30.1 GB
Memory %26%24%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
laguna-xs-2.1
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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
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