gpt-oss-20b
LM-STUDIO GGUFMar 6, 2026 · Apple M4 Pro
nemotron-3-nano
LM-STUDIO GGUFMar 6, 2026 · Apple M4 Pro
Global Score
95 vs 93
Hardware Fit
94 vs 100
Quality Score
95 vs 90
Hardware
gpt-oss-20b nemotron-3-nano
MachineMac miniMac mini
CPUApple M4 ProApple M4 Pro
Cores1414
RAM64 GB64 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss-20b nemotron-3-nano
Tokens/sec118.293.3
First chunk471 ms257 ms
TTFT2.2 s257 ms
Load timeN/AN/A
Memory usage11.3 GB0.1 GB
Memory %18%0%
HW Fit Score Breakdown
gpt-oss-20b
Speed
50/50
TTFT
14/20
Memory
30/30
nemotron-3-nano
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss-20b
Reasoning
19/20
Coding
18/20
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
Reasoning
19/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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