Back to leaderboard

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

gemma4:e2b

OLLAMA GGUF

gemma4 · 4.6B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

Global Score
92 vs 93
Hardware Fit
95 vs 100
Quality Score
90 vs 90

Hardware

qwen/qwen3-vl-30b gemma4:e2b
MachineASUSMicrosoft WSL
CPUAMD Ryzen 5 5500AMD Ryzen 5 5500
Cores1212
RAM31 GB8 GB
GPUNavi 44 [Radeon RX 9060 XT]Integrated / Unknown
OSNobara Linux 43Ubuntu 26.04.1 LTS
Archx64x64
Power Modeperformanceunknown

Performance

qwen/qwen3-vl-30b gemma4:e2b
Tokens/sec24.8141.2
First chunk11 ms94 ms
TTFT735 ms1.6 s
Load time11.7 s18.4 s
Memory usage0.6 GB0.2 GB
Memory %2%3%

HW Fit Score Breakdown

qwen/qwen3-vl-30b

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

gemma4:e2b

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

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

gemma4:e2b

Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3-vl-30b details | View gemma4:e2b 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