qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
76 vs 85
Hardware Fit
51 vs 100
Quality Score
87 vs 78
Hardware
qwen3-coder:latest gemma4:e2b
MachineDell Inc. Inspiron 15 3530Microsoft WSL
CPUIntel Gen Intel® Core™ i7-1355UAMD Ryzen 5 5500
Cores1212
RAM31 GB8 GB
GPURaptor Lake-P [Iris Xe Graphics]Integrated / Unknown
OScachyos rollingUbuntu 26.04.1 LTS
Archx64x64
Power Modelow-powerunknown
Performance
qwen3-coder:latest gemma4:e2b
Tokens/sec7.6139.2
First chunk2037 ms51 ms
TTFT2.0 s51 ms
Load time8.7 s28.5 s
Memory usage18.9 GB0.2 GB
Memory %61%3%
HW Fit Score Breakdown
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
gemma4:e2b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3-coder:latest
Reasoning
16/20
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
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
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