ST

starcoder2-15b-instruct-v0.1

StarCoderGGUF by mradermacherUpdated 2024-05-05
Download on Hugging Face
Parameters16B
Context16K
Layers40
Architecturestarcoder2
Smallest quant6.2 GB
Quick answer

starcoder2-15b-instruct-v0.1 needs about 11.0 GB of memory at Q4_K_M (a 9.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 6.2 GB (Q2_K) to 17.0 GB (Q8_0).

StarCoder2-15B-Instruct-v0.1 – a 15 B parameter code generation model

StarCoder2-15B-Instruct-v0.1 is a 15 B parameter model fine‑tuned for single‑turn coding instructions. It is trained on a self‑aligned instruction dataset and released under the bigcode‑openrail‑m license. The model is available in multiple GGUF quantizations.

Good at

  • Python code generation
  • Single‑turn coding instructions
  • Self‑aligned instruction responses

Limits

  • No vision support
  • Limited to coding instructions
  • Requires 8 k context for full performance

Best for

  • Writing Python functions
  • Generating code snippets
  • Debugging simple scripts

Who it’s for. Developers and researchers needing a code‑focused LLM that can be run locally. The model is suitable for projects that require a permissively licensed, self‑aligned code generation tool.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.2 GB 7.4 GB
Tight Get file →
IQ3_XS6.7 GB 7.9 GB
Tight Get file →
Q3_K_S7.0 GB 8.2 GB
Too big Get file →
IQ3_S7.0 GB 8.2 GB
Too big Get file →
IQ3_M7.3 GB 8.5 GB
Too big Get file →
Q3_K_M8.0 GB 9.2 GB
Too big Get file →
IQ4_XS8.7 GB 9.9 GB
Too big Get file →
Q3_K_L9.0 GB 10.1 GB
Too big Get file →
Q4_K_S9.2 GB 10.3 GB
Too big Get file →
Q4_K_M9.9 GB 11.0 GB
Too big Get file →
Q5_K_S11.0 GB 12.2 GB
Too big Get file →
Q5_K_M11.4 GB 12.6 GB
Too big Get file →
Q6_K13.1 GB 14.3 GB
Too big Get file →
Q8_017.0 GB 18.1 GB
Too big Get file →

For 8 GB VRAM use Q2_K (6.19 GB) or IQ3_XS (6.71 GB). For 12 GB VRAM use Q3_K_M (8.04 GB) or Q4_K_S (9.16 GB). For 16 GB VRAM use Q4_K_M (9.86 GB) or Q5_K_S (11.02 GB). Memory estimates are approximate.

What GPU do you need for starcoder2-15b-instruct-v0.1?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_XS (6.7 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (9.9 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (13.1 GB file, about 14.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (17.0 GB file, about 18.1 GB in use).

Which starcoder2-15b-instruct-v0.1 quant should you choose?

Q4_K_M is the usual starting point for starcoder2-15b-instruct-v0.1: it balances file size and quality well. Here it is a 9.9 GB file.

The Q8_0 file is 17.0 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 6.2 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

Architecturestarcoder2
Parameters16B
Layers40
Trained context16,384 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyStarCoder
Downloads (HF)2,142
Last updated2024-05-05

Frequently asked questions about starcoder2-15b-instruct-v0.1

How much VRAM does starcoder2-15b-instruct-v0.1 need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 9.9 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 starcoder2-15b-instruct-v0.1 on an 8 GB GPU?

Yes, with IQ3_XS: the 6.7 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of starcoder2-15b-instruct-v0.1 GGUF?

It depends on the quant: Q2_K is 6.2 GB, IQ3_XS is 6.7 GB, Q3_K_S is 7.0 GB, IQ3_S is 7.0 GB, IQ3_M is 7.3 GB, Q3_K_M is 8.0 GB and 8 more.

What context length does starcoder2-15b-instruct-v0.1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.7 GB at 8K and 1.3 GB at 16K.

Where can I download starcoder2-15b-instruct-v0.1 GGUF?

The files are on Hugging Face in the mradermacher/starcoder2-15b-instruct-v0.1-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 starcoder2-15b-instruct-v0.1 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 StarCoder2-15B-Instruct-v0.1 on 8 GB VRAM?

Yes, use the Q2_K or IQ3_XS quantization. The model file is 6.19 GB or 6.71 GB and requires about 7.4 GB or 7.9 GB of VRAM at 8 k context.

Does the model support other programming languages?

It is primarily fine‑tuned for Python. Support for other languages may be limited and less accurate.

What license applies to this model?

The model is released under the bigcode‑openrail‑m license.

Other GGUFs of starcoder2-15b-instruct-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More StarCoder models

All StarCoder →

Other medium models

All medium models →