Back to leaderboard

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

gemma-4-26b-a4b-it@iq3_xxs

LM-STUDIO GGUF

gemma4 · 26B · IQ3_XXS

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
78 vs 83
Hardware Fit
54 vs 58
Quality Score
88 vs 94

Hardware

qwen3-coder:30b-a3… gemma-4-26b-a4b-it…
MachineHP HP Pavilion Laptop 15-eh1xxxDocker Container
CPUAMD Ryzen 5 5500UIntel Gen Intel® Core™ i9-11900H
Cores1216
RAM63 GB15 GB
GPUAMD Radeon(TM) GraphicsTigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3-coder:30b-a3… gemma-4-26b-a4b-it…
Tokens/sec8.010.3
First chunk1468 ms8 ms
TTFT1.5 s3.5 s
Load time114.5 s10.9 s
Memory usage33.5 GB6.4 GB
Memory %53%41%

HW Fit Score Breakdown

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

gemma-4-26b-a4b-it@iq3_…

Speed
19/50
TTFT
12/20
Memory
27/30

Quality

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma-4-26b-a4b-it@iq3_…

Reasoning
18/20
Coding
19/20
Instruction
19/20
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