gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Global Score
83 vs 82
Hardware Fit
65 vs 81
Quality Score
90 vs 82
Hardware
gpt-oss:20b qwen3.5:9b
MachineMac miniAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1032
RAM24 GB125 GB
GPUApple M4Integrated / Apple Silicon
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gpt-oss:20b qwen3.5:9b
Tokens/sec17.130.8
First chunk705 ms195 ms
TTFT10.2 s195 ms
Load time23.1 s6.8 s
Memory usage13.1 GB18.8 GB
Memory %55%15%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
qwen3.5:9b
Speed
31/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5:9b
Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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