Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
82 vs 90
Hardware Fit
71 vs 82
Quality Score
87 vs 93

Hardware

qwen3-coder:30b gemma-4-26b-a4b-it…
MachineHP HP Pavilion Laptop 15-eh1xxxASUS
CPUAMD Ryzen 5 5500UAMD Ryzen 7 7800X3D 8-Core Processor
Cores1216
RAM63 GB31 GB
GPUAMD Radeon(TM) GraphicsNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

qwen3-coder:30b gemma-4-26b-a4b-it…
Tokens/sec14.3156.5
First chunk869 ms10 ms
TTFT869 ms124 ms
Load time0.3 sN/A
Memory usage20.5 GB23.3 GB
Memory %32%76%

HW Fit Score Breakdown

qwen3-coder:30b

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

gemma-4-26b-a4b-it-qat

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

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

gemma-4-26b-a4b-it-qat

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-coder:30b details | View gemma-4-26b-a4b-it… 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