Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 7, 2026 · AMD Ryzen 5 5500

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

Global Score
71 vs 46
Hardware Fit
56 vs 93
Quality Score
78 vs 26

Hardware

qwen3.5:9b gemma3:4b
MachineSystem manufacturerNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 5 5500Cortex-A78AE
Cores126
RAM16 GB7 GB
GPUNVIDIA GeForce RTX 3060Integrated / Unknown
OSMicrosoft Windows 11 IoT Enterprise LTSC 10.0.26100Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:9b gemma3:4b
Tokens/sec5.314.9
First chunk1624 ms2204 ms
TTFT1.6 s2.2 s
Load time4.0 s2.0 s
Memory usage7.9 GB2.6 GB
Memory %50%35%

HW Fit Score Breakdown

qwen3.5:9b

Speed
11/50
TTFT
20/20
Memory
25/30

gemma3:4b

Speed
45/50
TTFT
19/20
Memory
29/30

Quality

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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

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