Back to leaderboard

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
92 vs 62
Hardware Fit
95 vs 77
Quality Score
90 vs 55

Hardware

qwen/qwen3-vl-30b google/gemma-4-e4b
MachineASUSLENOVO 82JQ
CPUAMD Ryzen 5 5500AMD Ryzen 7 5800H
Cores1216
RAM31 GB16 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 3060 Laptop GPU
OSNobara Linux 43Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modeperformancebalanced

Performance

qwen/qwen3-vl-30b google/gemma-4-e4b
Tokens/sec24.827.6
First chunk11 ms23 ms
TTFT735 ms480 ms
Load time11.7 sN/A
Memory usage0.6 GB13.2 GB
Memory %2%83%

HW Fit Score Breakdown

qwen/qwen3-vl-30b

Speed
45/50
TTFT
20/20
Memory
30/30

google/gemma-4-e4b

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

Quality

qwen/qwen3-vl-30b

Reasoning
19/20
Coding
19/20
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

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 qwen/qwen3-vl-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