gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
nemotron-3-nano:4b
OLLAMA GGUFnemotron_h · 4.0B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
87 vs 84
Hardware Fit
83 vs 99
Quality Score
88 vs 78
Hardware
gpt-oss:20b nemotron-3-nano:4b
MachineMac miniMicrosoft WSL
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM24 GB8 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
gpt-oss:20b nemotron-3-nano:4b
Tokens/sec24.3109.2
First chunk529 ms349 ms
TTFT4.5 s349 ms
Load time11.2 s7.8 s
Memory usage13.1 GB2.6 GB
Memory %55%34%
HW Fit Score Breakdown
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
nemotron-3-nano:4b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
11/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
nemotron-3-nano:4b
Reasoning
16/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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