gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
Global Score
81 vs 92
Hardware Fit
100 vs 95
Quality Score
73 vs 90
Hardware
gemma3n:latest qwen/qwen3-vl-30b
MachineSupermicro AS -2015HS-TNRASUS
CPUAMD EPYC 9654P 96-Core ProcessorAMD Ryzen 5 5500
Cores6412
RAM128 GB31 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Navi 44 [Radeon RX 9060 XT]
OSUbuntu 24.04.3 LTSNobara Linux 43
Archx64x64
Power Modeperformanceperformance
Performance
gemma3n:latest qwen/qwen3-vl-30b
Tokens/sec108.724.8
First chunk333 ms11 ms
TTFT333 ms735 ms
Load time4.5 s11.7 s
Memory usage8.6 GB0.6 GB
Memory %7%2%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
Quality
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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