Back to leaderboard

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

nemotron-3-nano:4b

OLLAMA GGUF

nemotron_h · 4.0B · Q4_K_M

Excellent

Aug 26, 2026 · Apple M1 Pro

Global Score
74 vs 93
Hardware Fit
99 vs 95
Quality Score
63 vs 92

Hardware

llama3.2:3b nemotron-3-nano:4b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M1 Pro
Cores610
RAM7 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 22.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

llama3.2:3b nemotron-3-nano:4b
Tokens/sec21.131.7
First chunk1032 ms270 ms
TTFT1.0 s2.9 s
Load time8.4 s2.1 s
Memory usage2.4 GB4.1 GB
Memory %32%25%

HW Fit Score Breakdown

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

nemotron-3-nano:4b

Speed
50/50
TTFT
15/20
Memory
30/30

Quality

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

nemotron-3-nano:4b

Reasoning
18/20
Coding
17/20
Instruction
17/20
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest