Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

unsloth/gemma-4-12b-it-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_K_XL

Good

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

Global Score
82 vs 75
Hardware Fit
71 vs 48
Quality Score
87 vs 86

Hardware

qwen3-coder:30b unsloth/gemma-4-12…
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 unsloth/gemma-4-12…
Tokens/sec14.36.0
First chunk869 ms27 ms
TTFT869 ms5.1 s
Load time0.3 s8.4 s
Memory usage20.5 GB0.0 GB
Memory %32%0%

HW Fit Score Breakdown

qwen3-coder:30b

Speed
22/50
TTFT
20/20
Memory
29/30

unsloth/gemma-4-12b-it-…

Speed
10/50
TTFT
8/20
Memory
30/30

Quality

qwen3-coder:30b

Reasoning
16/20
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: Strong Multilingual: Strong

unsloth/gemma-4-12b-it-…

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-coder:30b details | View unsloth/gemma-4-12… 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