openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
qwen36-distill-apex
OLLAMA GGUFJul 17, 2026 · Apple M5 Max
Global Score
90 vs 36
Hardware Fit
88 vs 100
Quality Score
91 vs 8
Hardware
openai/gpt-oss-20b qwen36-distill-apex
MachineASUSMacBook Pro
CPUAMD Ryzen 5 5500Apple M5 Max
Cores1218
RAM31 GB64 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M5 Max
OSNobara Linux 43macOS 27.0
Archx64arm64
Power Modeperformancebalanced
Performance
openai/gpt-oss-20b qwen36-distill-apex
Tokens/sec58.755.2
First chunk6 ms210 ms
TTFT4.5 s210 ms
Load timeN/A4.8 s
Memory usage11.9 GB0.9 GB
Memory %38%2%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
qwen36-distill-apex
Speed
50/50
TTFT
20/20
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
qwen36-distill-apex
Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor 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