Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
85 vs 78
Hardware Fit
96 vs 47
Quality Score
80 vs 92

Hardware

qwen3.5:9b gemma4:31b
MachineASUSAZW GTR Pro
CPUIntel Core™ i5-14600KFAMD RYZEN AI MAX+ 395
Cores2032
RAM32 GB125 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERRadeon 8060S
OSMicrosoft Windows 11 Famille 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3.5:9b gemma4:31b
Tokens/sec88.69.8
First chunk306 ms873 ms
TTFT306 ms873 ms
Load time7.0 s7.0 s
Memory usage8.1 GB68.3 GB
Memory %25%55%

HW Fit Score Breakdown

qwen3.5:9b

Speed
50/50
TTFT
20/20
Memory
26/30

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

Quality

qwen3.5:9b

Reasoning
14/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:9b details | View gemma4:31b 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