StarCoder 2 15B
StarCoder 2 flagship. The largest BigCode coder; 16k context with strong fill-in-middle.
Overview
StarCoder 2 flagship. The largest BigCode coder; 16k context with strong fill-in-middle.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- Permissive license at 15B
Weaknesses
- Qwen 2.5 Coder 14B/32B leads on most code benchmarks
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 9.0 GB | 14 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of StarCoder 2 15B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run StarCoder 2 15B?
Can I use StarCoder 2 15B commercially?
What's the context length of StarCoder 2 15B?
Source: huggingface.co/bigcode/starcoder2-15b
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify StarCoder 2 15B runs on your specific hardware before committing money.