starcoder2 3b needs about 2.6 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 1.2 GB (Q2_K) to 3.2 GB (Q8_0).
StarCoder2 3B – a 3B‑parameter code generation model
StarCoder2 3B is a 3.03B parameter model trained on 17 programming languages from The Stack v2. It uses Grouped Query Attention and a 16,384 token context window. The model is not an instruction model and is best used for code completion tasks.
Good at
- Code completion
- Programming language support
- Large context window
Limits
- Not an instruction model
- No vision support
- Requires 8,000 token context for memory estimates
Best for
- Writing functions
- Debugging code snippets
- Generating code examples
Who it’s for. Developers and researchers needing a lightweight code generation model. It is suitable for local inference with llama.cpp and for integration into code editors.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q4_1 | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_0 | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q5_K_S | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 2.9 GB | Fits | Get file → | |
| Q5_1 | 2.3 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.2 GB | Fits | Get file → | |
| Q8_0 | 3.2 GB | 4.0 GB | Fits | Get file → |
For 8 GB VRAM, Q4_0 or Q4_K_S (1.75 GB or 1.76 GB) are recommended, using about 2.5 GB of VRAM at 8 k context. If more memory is available, Q5_0 or Q5_K_S (2.11 GB) provide higher quality. Larger quants like Q6_K or Q8_0 exceed typical 8 GB limits.
What GPU do you need for starcoder2 3b?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.0 GB in use).
Which starcoder2 3b quant should you choose?
Q4_K_M is the usual starting point for starcoder2 3b: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.2 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 1.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about starcoder2 3b
How much VRAM does starcoder2 3b need?
About 2.6 GB at Q4_K_M with an 8K context window. That is the 1.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run starcoder2 3b on an 8 GB GPU?
Yes, with Q8_0: the 3.2 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of starcoder2 3b GGUF?
It depends on the quant: Q2_K is 1.2 GB, Q3_K_S is 1.4 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, Q4_0 is 1.7 GB, Q4_K_S is 1.8 GB and 8 more.
What context length does starcoder2 3b support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.5 GB at 16K.
Where can I download starcoder2 3b GGUF?
The files are on Hugging Face in the QuantFactory/starcoder2-3b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does starcoder2 3b use?
Hugging Face lists the license as bigcode-openrail-m. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run StarCoder2 3B on 8 GB VRAM?
Yes, using Q4_0 or Q4_K_S quants which use about 2.5 GB of VRAM at 8 k context. Other quants require more memory.
Does StarCoder2 3B support natural language instructions?
No, it is not an instruction model and does not respond well to natural language prompts.
What is the context window size?
The model supports a context window of 16,384 tokens with a sliding window of 4,096 tokens.