openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
Global Score
90 vs 33
Hardware Fit
88 vs 50
Quality Score
91 vs 25
Hardware
openai/gpt-oss-20b gemma4:26b
MachineASUSMac mini
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM31 GB24 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4
OSNobara Linux 43macOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
openai/gpt-oss-20b gemma4:26b
Tokens/sec58.720.0
First chunk6 ms941 ms
TTFT4.5 s30.0 s
Load timeN/A0.2 s
Memory usage11.9 GB20.3 GB
Memory %38%85%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:26b
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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