BigCode·3 sizes·Coding LLM
StarCoder models: sizes & hardware to run them
The StarCoder family spans 3 sizes from 3B to 15B. Each size maps to a different hardware tier — below is the approximate memory each needs at 4-bit and the device we’d start with for a private local deployment.
Code
Sizes & hardware
| Model | Params | Context | ~VRAM @ 4-bit | Minimum device | Recommended |
|---|---|---|---|---|---|
| StarCoder2 3B | 3B | 16K | ~2.2GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
| StarCoder2 7B | 7B | 16K | ~5GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
| StarCoder2 15B | 15B | 16K | ~10GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
Memory figures are approximate working-set estimates (weights + KV cache at modest context); treat as ±. Device picks come from our compatibility engine, best on-prem fit first.
Open each size
Coding LLM
StarCoder2 3B
Runs on a CPU or any small GPU. A tiny code model for fast, private completion.
Coding LLM
StarCoder2 7B
8GB+ GPUs at 4-bit. A small code model for responsive private completion.
Coding LLM
StarCoder2 15B
16GB+ GPUs at 4-bit. The largest StarCoder2 for stronger completion on one card.
Run StarCoder models inside a private AI Business OS
Run your own AI agents on hardware you control — private by design, no per-seat data leaving your premises. BrainOutput helps you pick the right machine and turn it into a working AI Business OS.
Explore the AI Business OS