Back to leaderboard

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Excellent

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
90 vs 78
Hardware Fit
89 vs 47
Quality Score
90 vs 92

Hardware

qwen3-coder:30b-a3… gemma4:31b
MachineMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJGAZW GTR Pro
CPUIntel Core™ Ultra 9 285HXAMD RYZEN AI MAX+ 395
Cores2432
RAM63 GB125 GB
GPUIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPURadeon 8060S
OSMicrosoft Windows 11 Home Single Language 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3-coder:30b-a3… gemma4:31b
Tokens/sec43.19.8
First chunk957 ms873 ms
TTFT957 ms873 ms
Load time52.0 s7.0 s
Memory usage33.6 GB68.3 GB
Memory %53%55%

HW Fit Score Breakdown

qwen3-coder:30b-a3b-q8_0

Speed
46/50
TTFT
19/20
Memory
24/30

gemma4:31b

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

Quality

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong 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

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