dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-12 23:54:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

feat: Add quantization performance chart using Chart.js and quant.yml data

Browse source
This commit is contained in:
Paul Gauthier (aider) 2024-11-21 10:57:03 -08:00
parent 8eda09533d
commit 7fba332f58
2 changed files with 43 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
aider/website/_posts/2024-11-21-quantization.md
View file

@ -21,7 +21,8 @@ and local model servers like ollama.
The graph below compares 4 different versions of the Qwen 2.5 32B model,
served both locally and from cloud providers:
- Qwen2.5-Coder-32B-Instruct
- ollama/qwen2.5:32b
- ollama/qwen2.5:32b-instruct-q8_0
- openrouter/qwen/qwen-2.5-coder-32b-instruct
<canvas id="quantChart" width="800" height="450" style="margin: 20px 0"></canvas>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script>
{% include quant-chart.js %}
</script>