Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jun 5, 2026 · AMD Ryzen 7 5800H

Global Score
57 vs 89
Hardware Fit
61 vs 83
Quality Score
55 vs 92

Hardware

qwen3.5:9b gemma4:latest
MachineAZW GTR ProLENOVO 82JQ
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 5800H
Cores3216
RAM125 GB16 GB
GPUAMD Radeon 8060SNVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:9b gemma4:latest
Tokens/sec30.346.3
First chunk205 ms824 ms
TTFT8.7 s3.8 s
Load time5.6 s21.0 s
Memory usage18.8 GB8.9 GB
Memory %15%56%

HW Fit Score Breakdown

qwen3.5:9b

Speed
30/50
TTFT
1/20
Memory
30/30

gemma4:latest

Speed
50/50
TTFT
11/20
Memory
22/30

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

gemma4:latest

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:9b details | View gemma4:latest 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