gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Oct 11, 2026 · AMD Ryzen 5 5500

Global Score

46 vs 74

Hardware Fit

93 vs 100

Quality Score

26 vs 63

Hardware

gemma3:4b qwen3:0.6b

MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMicrosoft WSL

CPUCortex-A78AEAMD Ryzen 5 5500

Cores612

RAM7 GB8 GB

GPUIntegrated / UnknownIntegrated / Unknown

OSUbuntu 22.04.5 LTSUbuntu 26.04.1 LTS

Archarm64x64

Power Modebalancedunknown

Performance

gemma3:4b qwen3:0.6b

Tokens/sec14.9249.5

First chunk2204 ms80 ms

TTFT2.2 s659 ms

Load time2.0 s6.3 s

Memory usage2.6 GB0.9 GB

Memory %35%11%

HW Fit Score Breakdown

gemma3:4b

Speed

45/50

TTFT

19/20

Memory

29/30

qwen3:0.6b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

gemma3:4b

Reasoning

11/20

Coding

11/20

Instruction

0/20

Structured

0/15

Math

4/15

Multilingual

0/10

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

qwen3:0.6b

Reasoning

13/20

Coding

6/20

Instruction

12/20

Structured

13/15

Math

12/15

Multilingual

7/10

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

View gemma3:4b details | View qwen3:0.6b 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