gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
qwen3-vl:30b
OLLAMA GGUFqwen3vlmoe · 31.1B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
85 vs 80
Hardware Fit
100 vs 98
Quality Score
78 vs 72
Hardware
gemma4:e2b qwen3-vl:30b
MachineMicrosoft WSLASUS
CPUAMD Ryzen 5 5500Intel Core™ Ultra 9 285K
Cores1224
RAM8 GB47 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeunknownbalanced
Performance
gemma4:e2b qwen3-vl:30b
Tokens/sec139.2208.9
First chunk51 ms102 ms
TTFT51 ms684 ms
Load time28.5 s0.1 s
Memory usage0.2 GB22.0 GB
Memory %3%47%
HW Fit Score Breakdown
gemma4:e2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-vl:30b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
gemma4:e2b
Reasoning
13/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3-vl:30b
Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak 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