llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score

74 vs 66

Hardware Fit

99 vs 40

Quality Score

63 vs 77

Hardware

llama3.2:3b gemma4:31b

MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUSTeK COMPUTER INC. GX10

CPUCortex-A78AECortex-X925

Cores620

RAM7 GB122 GB

GPUIntegrated / UnknownDevice 2e12

OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS

Archarm64arm64

Power Modebalancedperformance

Performance

llama3.2:3b gemma4:31b

Tokens/sec21.110.7

First chunk1032 ms983 ms

TTFT1.0 s20.3 s

Load time8.4 s8.8 s

Memory usage2.4 GB21.4 GB

Memory %32%18%

HW Fit Score Breakdown

llama3.2:3b

Speed

50/50

TTFT

20/20

Memory

29/30

gemma4:31b

Speed

10/50

TTFT

0/20

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

gemma4:31b

Reasoning

14/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

10/15

Multilingual

9/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

View llama3.2:3b details | View gemma4:31b details

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