gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
Global Score
94 vs 76
Hardware Fit
91 vs 82
Quality Score
95 vs 73
Hardware
gpt-oss:20b gemma4:e2b
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)LENOVO 20U30029MB
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-10210U
Cores328
RAM64 GB15 GB
GPUAMD Radeon(TM) 8060S GraphicsCometLake-U GT2 [UHD Graphics]
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200Pop 24.04 LTS
Archx64x64
Power Modebalancedperformance
Performance
gpt-oss:20b gemma4:e2b
Tokens/sec48.013.5
First chunk357 ms1270 ms
TTFT2.3 s1.3 s
Load time0.2 s13.4 s
Memory usage16.4 GB6.5 GB
Memory %26%42%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
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
gemma4:e2b
Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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