gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
93 vs 80
Hardware Fit
100 vs 60
Quality Score
90 vs 88
Hardware
gemma4:e2b qwen3-coder:30b
MachineMicrosoft WSLASUS
CPUAMD Ryzen 5 5500Intel Gen Intel® Core™ i7-12700K
Cores1220
RAM8 GB96 GB
GPUIntegrated / UnknownParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modeunknownbalanced
Performance
gemma4:e2b qwen3-coder:30b
Tokens/sec141.214.7
First chunk94 ms796 ms
TTFT1.6 s796 ms
Load time18.4 s0.2 s
Memory usage0.2 GB17.9 GB
Memory %3%19%
HW Fit Score Breakdown
gemma4:e2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
Quality
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
qwen3-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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