qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score

57 vs 76

Hardware Fit

61 vs 92

Quality Score

55 vs 69

Hardware

qwen3.5:9b gemma3:4b

MachineAZW GTR ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUAMD RYZEN AI MAX+ 395Cortex-A78AE

Cores326

RAM125 GB7 GB

GPUAMD Radeon 8060SIntegrated / Unknown

OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS

Archx64arm64

Power Modelow-powerbalanced

Performance

qwen3.5:9b gemma3:4b

Tokens/sec30.315.0

First chunk205 ms2380 ms

TTFT8.7 s2.4 s

Load time5.6 s13.6 s

Memory usage18.8 GB2.6 GB

Memory %15%35%

HW Fit Score Breakdown

qwen3.5:9b

Speed

30/50

TTFT

1/20

Memory

30/30

gemma3:4b

Speed

45/50

TTFT

18/20

Memory

29/30

Quality

qwen3.5:9b

Reasoning

17/20

Coding

2/20

Instruction

7/20

Structured

8/15

Math

12/15

Multilingual

9/10

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

gemma3:4b

Reasoning

11/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

4/15

Multilingual

10/10

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

View qwen3.5:9b details | View gemma3:4b 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