gemma3:1b

OLLAMA GGUF

gemma3 · 999.89M · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score

59 vs 65

Hardware Fit

100 vs 73

Quality Score

42 vs 62

Hardware

gemma3:1b qwen3.5:4b

MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperAZW GTR Pro

CPUCortex-A78AEAMD RYZEN AI MAX+ 395

Cores632

RAM7 GB125 GB

GPUIntegrated / UnknownAMD Radeon 8060S

OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedlow-power

Performance

gemma3:1b qwen3.5:4b

Tokens/sec34.045.7

First chunk1876 ms180 ms

TTFT1.9 s30.0 s

Load time1.7 s5.3 s

Memory usage0.8 GB16.2 GB

Memory %11%13%

HW Fit Score Breakdown

gemma3:1b

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3.5:4b

Speed

43/50

TTFT

0/20

Memory

30/30

Quality

gemma3:1b

Reasoning

7/20

Coding

5/20

Instruction

15/20

Structured

7/15

Math

1/15

Multilingual

7/10

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

qwen3.5:4b

Reasoning

17/20

Coding

1/20

Instruction

13/20

Structured

8/15

Math

13/15

Multilingual

10/10

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

View gemma3:1b details | View qwen3.5:4b 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