Starcoderplus needs about 10.8 GB of memory at Q4_K_M (a 10.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 3.7 GB (IQ1_S) to 13.1 GB (Q6_K).
Starcoderplus – 15.8B coding‑focused LLM in GGUF format
Starcoderplus is a 15.8B parameter model optimized for code generation. It supports a 8192 token context window and is available in multiple quantizations. The model is provided as GGUF files by mradermacher.
Good at
- Code generation
- Programming assistance
- Language‑specific coding tasks
Limits
- No vision support
- License not specified
- Requires 8k context for full performance
Best for
- Writing boilerplate code
- Debugging assistance
- Learning new programming languages
Who it’s for. Developers and researchers needing a large, code‑centric model that can run locally. The model is suitable for those who can manage the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.7 GB | 4.3 GB | Fits | Get file → | |
| IQ1_M | 4.0 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XXS | 4.5 GB | 5.2 GB | Fits | Get file → | |
| IQ2_XS | 4.9 GB | 5.6 GB | Fits | Get file → | |
| IQ2_S | 5.3 GB | 5.9 GB | Fits | Get file → | |
| IQ2_M | 5.7 GB | 6.3 GB | Fits | Get file → | |
| Q2_K | 6.3 GB | 7.0 GB | Fits | Get file → | |
| IQ3_XXS | 6.4 GB | 7.1 GB | Fits | Get file → | |
| IQ3_XS | 6.9 GB | 7.6 GB | Tight | Get file → | |
| IQ3_S | 7.1 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_S | 7.1 GB | 7.8 GB | Tight | Get file → | |
| IQ3_M | 7.6 GB | 8.3 GB | Too big | Get file → | |
| Q3_K_M | 8.4 GB | 9.0 GB | Too big | Get file → | |
| IQ4_XS | 8.7 GB | 9.3 GB | Too big | Get file → | |
| Q4_0 | 9.2 GB | 9.9 GB | Too big | Get file → | |
| Q4_K_S | 9.3 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_L | 9.3 GB | 9.9 GB | Too big | Get file → | |
| Q4_K_M | 10.1 GB | 10.8 GB | Too big | Get file → | |
| Q5_K_S | 11.1 GB | 11.8 GB | Too big | Get file → | |
| Q5_K_M | 11.7 GB | 12.4 GB | Too big | Get file → | |
| Q6_K | 13.1 GB | 13.8 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (file size 3.68 GB, memory 4.3 GB). For 12‑GB VRAM, IQ2_M (file size 5.66 GB, memory 6.3 GB) or Q3_K_M (file size 8.36 GB, memory 9 GB). Higher‑quality quants such as Q5_K_M (file size 11.7 GB, memory 12.4 GB) need 16‑GB VRAM or more.
What GPU do you need for Starcoderplus?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is IQ2_S (5.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_S (7.1 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_S (11.1 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (13.1 GB file, about 13.8 GB in use).
Which Starcoderplus quant should you choose?
Q4_K_M is the usual starting point for Starcoderplus: it balances file size and quality well. Here it is a 10.1 GB file.
If memory is tight, the smallest file is IQ1_S at 3.7 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 Starcoderplus
How much VRAM does Starcoderplus need?
About 10.8 GB at Q4_K_M with an 8K context window. That is the 10.1 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 Starcoderplus on an 8 GB GPU?
Yes, with IQ3_S: the 7.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Starcoderplus GGUF?
It depends on the quant: IQ1_S is 3.7 GB, IQ1_M is 4.0 GB, IQ2_XXS is 4.5 GB, IQ2_XS is 4.9 GB, IQ2_S is 5.3 GB, IQ2_M is 5.7 GB and 15 more.
What context length does Starcoderplus support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.
Where can I download Starcoderplus GGUF?
The files are on Hugging Face in the mradermacher/starcoderplus-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Starcoderplus on 8 GB VRAM?
Yes, using the IQ1_S quantization which requires about 4.3 GB of VRAM at 8k context.
Does Starcoderplus support image input?
No, the model has no vision capabilities.