nvidia/nemotron-3-nano
LM-STUDIO MLXnemotron_h · 30B · 4bit
Mar 4, 2026 · Apple M4
starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
84 vs 39
Hardware Fit
100 vs 100
Quality Score
77 vs 13
Hardware
nvidia/nemotron-3-… starcoder2:3b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
nvidia/nemotron-3-… starcoder2:3b
Tokens/sec47.949.4
First chunk465 msN/A
TTFT465 ms155 ms
Load timeN/A0.4 s
Memory usage16.6 GB3.0 GB
Memory %52%9%
HW Fit Score Breakdown
nvidia/nemotron-3-nano
Speed
50/50
TTFT
20/20
Memory
30/30
starcoder2:3b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
nvidia/nemotron-3-nano
Reasoning
13/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
starcoder2:3b
Reasoning
0/20
Coding
2/20
Instruction
5/20
Structured
2/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak 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