SOURCE-REVIEWED MODEL PROFILE
Qwen2.5-Coder-14B-Instruct
A larger dense coder for machines with more memory; select an appropriate quantization.
Metadata reviewed 2026-10-28 · Original creator: Qwen
What it does
- Coding
- Original publisher checkpoint; compatible conversions may have separate requirements
- Source-reviewed catalogue entry; not an installed service
Local fit
Plan RAM and VRAM for the selected artifact. Start with a small request and the runtime recommended by the publisher. This profile does not download weights or start an endpoint.
Context and output limits depend on the checkpoint, preprocessing and runtime. No universal memory-fit promise is made.
Evidence and limits
Source reviewed on October 28, 2026. We have not benchmarked this exact checkpoint locally.
Catalogue only. Use a supported runtime; no one-click installation or tested launcher adapter is claimed.
License and source
Keep publisher attribution and follow the exact checkpoint license. Runtime code and model weights have separate terms.
Read the original model card ↗
Reviewed source revision: aedcc2d42b622764e023cf882b6652e646b95671