openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
nemotron-3-nano:4b
OLLAMA GGUFnemotron_h · 4.0B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
91 vs 95
Hardware Fit
90 vs 99
Quality Score
91 vs 93
Hardware
openai/gpt-oss-20b nemotron-3-nano:4b
MachineMacBook ProMicrosoft WSL
CPUApple M3 MaxAMD Ryzen 5 5500
Cores1612
RAM128 GB8 GB
GPUApple M3 MaxIntegrated / Unknown
OSmacOS 27.2Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
openai/gpt-oss-20b nemotron-3-nano:4b
Tokens/sec95.1107.6
First chunk3 ms361 ms
TTFT2.5 s1.1 s
Load time9.2 s7.9 s
Memory usage0.0 GB2.6 GB
Memory %0%34%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
nemotron-3-nano:4b
Speed
50/50
TTFT
20/20
Memory
29/30
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: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
nemotron-3-nano:4b
Reasoning
19/20
Coding
16/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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