gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score

77 vs 29

Hardware Fit

59 vs 86

Quality Score

84 vs 4

Hardware

gemma4:12b qwen3:4b

MachineASUSTeK COMPUTER INC. GX10NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUCortex-X925Cortex-A78AE

Cores206

RAM122 GB7 GB

GPUDevice 2e12Integrated / Unknown

OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS

Archarm64arm64

Power Modeperformancebalanced

Performance

gemma4:12b qwen3:4b

Tokens/sec26.817.9

First chunk632 ms1010 ms

TTFT30.0 s6.4 s

Load time5.4 s9.5 s

Memory usage9.3 GB3.0 GB

Memory %8%40%

HW Fit Score Breakdown

gemma4:12b

Speed

29/50

TTFT

0/20

Memory

30/30

qwen3:4b

Speed

50/50

TTFT

8/20

Memory

28/30

Quality

gemma4:12b

Reasoning

17/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

13/15

Multilingual

10/10

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

qwen3:4b

Reasoning

4/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

0/15

Multilingual

0/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

View gemma4:12b details | View qwen3:4b 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