qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
Global Score
92 vs 76
Hardware Fit
95 vs 82
Quality Score
90 vs 73
Hardware
qwen/qwen3-vl-30b gemma4:e2b
MachineASUSLENOVO 20U30029MB
CPUAMD Ryzen 5 5500Intel Core™ i5-10210U
Cores128
RAM31 GB15 GB
GPUNavi 44 [Radeon RX 9060 XT]CometLake-U GT2 [UHD Graphics]
OSNobara Linux 43Pop 24.04 LTS
Archx64x64
Power Modeperformanceperformance
Performance
qwen/qwen3-vl-30b gemma4:e2b
Tokens/sec24.813.5
First chunk11 ms1270 ms
TTFT735 ms1.3 s
Load time11.7 s13.4 s
Memory usage0.6 GB6.5 GB
Memory %2%42%
HW Fit Score Breakdown
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
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
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest