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 21 quants, from 0.7 GB (IQ1_S) to 2.5 GB (Q6_K).
Starcoder2 3B – 3B‑parameter code generation model
Starcoder2 3B is a 3.03‑billion parameter transformer decoder trained on 17 programming languages. It uses grouped‑query attention and a 16,384‑token context window with a sliding window of 4,096 tokens. The model is not an instruction model and is best used for code completion tasks.
Good at
- Code completion
- Fill‑in‑the‑Middle generation
- Supports 17 programming languages
Limits
- Not an instruction model
- Limited to code generation
- Requires at least 8 k context for memory estimates
Best for
- Developers needing code snippets
- Fine‑tuning on custom codebases
- Local code generation with GGUF
Who it’s for. Developers and researchers who need a lightweight code model for local inference. The model runs in GGUF format and can be used with llama.cpp or bitsandbytes for quantized inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.7 GB | 1.5 GB | Fits | Get file → | |
| IQ1_M | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ2_XXS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ2_XS | 1.0 GB | 1.7 GB | Fits | Get file → | |
| IQ2_S | 1.0 GB | 1.8 GB | Fits | Get file → | |
| IQ2_M | 1.1 GB | 1.8 GB | Fits | Get file → | |
| IQ3_XXS | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q2_K | 1.2 GB | 2.0 GB | Fits | Get file → | |
| IQ3_XS | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.1 GB | Fits | Get file → | |
| IQ3_S | 1.4 GB | 2.1 GB | Fits | Get file → | |
| IQ3_M | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.3 GB | Fits | Get file → | |
| IQ4_XS | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.8 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 → | |
| Q5_K_S | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 2.9 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.2 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (0.71 GB) or IQ1_M (0.77 GB). For 12 GB VRAM, IQ2_S (1 GB) or Q2_K (1.22 GB) are suitable. For 16 GB VRAM, Q4_K_M (1.89 GB) or Q5_K_M (2.18 GB) provide higher quality while staying within memory limits. Estimates are approximate.
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 Q6_K (2.5 GB file, about 3.2 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.
If memory is tight, the smallest file is IQ1_S at 0.7 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 Q6_K: the 2.5 GB file needs about 3.2 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: IQ1_S is 0.7 GB, IQ1_M is 0.8 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.0 GB, IQ2_M is 1.1 GB and 15 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 mradermacher/starcoder2-3b-i1-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, use a quant like IQ1_S or IQ1_M; they require about 1.5 GB of VRAM at 8 k context.
Is Starcoder2 3B an instruction model?
No, it is trained on code and performs best with code completion prompts.
What license applies to Starcoder2 3B?
The model is released under the bigcode‑openrail‑m license.