openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
gemma3:12b
OLLAMA GGUFgemma3 · 12.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
90 vs 80
Hardware Fit
88 vs 83
Quality Score
91 vs 78
Hardware
openai/gpt-oss-20b gemma3:12b
MachineASUSMacBook Air
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4
OSNobara Linux 43macOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
openai/gpt-oss-20b gemma3:12b
Tokens/sec58.712.7
First chunk6 msN/A
TTFT4.5 s560 ms
Load timeN/A2.8 s
Memory usage11.9 GB11.0 GB
Memory %38%34%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
gemma3:12b
Speed
23/50
TTFT
30/20
Memory
30/30
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
gemma3:12b
Reasoning
14/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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