openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
Global Score
90 vs 34
Hardware Fit
88 vs 58
Quality Score
91 vs 23
Hardware
openai/gpt-oss-20b qwen3.5:latest
MachineASUSMac mini
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM31 GB16 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4
OSNobara Linux 43macOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
openai/gpt-oss-20b qwen3.5:latest
Tokens/sec58.713.3
First chunk6 ms438 ms
TTFT4.5 s19.8 s
Load timeN/A0.2 s
Memory usage11.9 GB8.0 GB
Memory %38%50%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
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
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor 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