qwen2.5-coder:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Nov 13, 2026 · Intel Core™ i5-4590T
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
59 vs 80
Hardware Fit
100 vs 60
Quality Score
41 vs 88
Hardware
qwen2.5-coder:0.5b qwen3-coder:30b
MachineFUJITSU ESPRIMO Q920ASUS
CPUIntel Core™ i5-4590TIntel Gen Intel® Core™ i7-12700K
Cores420
RAM16 GB96 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen2.5-coder:0.5b qwen3-coder:30b
Tokens/sec43.714.7
First chunk290 ms796 ms
TTFT290 ms796 ms
Load time1.4 s0.2 s
Memory usage0.9 GB17.9 GB
Memory %6%19%
HW Fit Score Breakdown
qwen2.5-coder:0.5b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
Quality
qwen2.5-coder:0.5b
Reasoning
7/20
Coding
8/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
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