qwen2.5-coder:0.5b

qwen2 · 494.03M · Q4_K_M

FUJITSU ESPRIMO Q920 (Intel Core™ i5-4590T)

16 GB · Microsoft Windows 10 Pro 10.0.19045

Tested on November 13, 2026

Top 82% Compare

Global Score

59 /100

Marginal

Hardware Fit

100/100

Quality

41/100

Get this model

🦙

Ollama

ollama pull qwen2.5-coder:0.5b

View on Ollama Library

ollama.com/library/qwen2.5-coder

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: FUJITSU ESPRIMO Q920
CPU: Intel Core™ i5-4590T
Cores: 4 total (4 perf)
Frequency: 2 GHz
RAM: 16 GB DDR3
GPU: Intel(R) HD Graphics 4600, Microsoft Remote Display Adapter
OS: Microsoft Windows 10 Pro 10.0.19045
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 43.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.6
First chunk latency Delay before the first streamed chunk arrives from runtime: 290 ms
Time to first token How fast the model starts responding — lower is better: 290 ms
Load time Time to load the model into memory before inference: 1.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.9 GB (6%)
Total tokens Total number of tokens generated across all benchmark prompts: 1023

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

7/20

Coding

8/20

Instruction following

10/20

Structured output

10/15

Math

2/15

Multilingual

4/10

Category levels

Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.40.14
Model format: GGUF
Hardware profile: ENTRY
Result hash: 3e380fe0e9d115f99ee3ca2f5dfd42ef65580adee3121fe7a631ae4a1e36d056

Interpretation

Hardware fit: 100/100. Overall suitability: MARGINAL (Global 59/100). Category profile: Reasoning: Weak, Coding: Weak, Instruction Following: Adequate, Structured Output: Adequate, Math: Poor, Multilingual: Weak.

Bench Environment

CPU load: avg 82% (peak 100%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest