Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
82 vs 62
Hardware Fit
71 vs 77
Quality Score
87 vs 55

Hardware

qwen3-coder:30b google/gemma-4-e4b
MachineHP HP Pavilion Laptop 15-eh1xxxLENOVO 82JQ
CPUAMD Ryzen 5 5500UAMD Ryzen 7 5800H
Cores1216
RAM63 GB16 GB
GPUAMD Radeon(TM) GraphicsNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-coder:30b google/gemma-4-e4b
Tokens/sec14.327.6
First chunk869 ms23 ms
TTFT869 ms480 ms
Load time0.3 sN/A
Memory usage20.5 GB13.2 GB
Memory %32%83%

HW Fit Score Breakdown

qwen3-coder:30b

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

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

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

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View qwen3-coder:30b details | View google/gemma-4-e4b 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