ST

Starcoder2 3b

StarCoderGGUF by mradermacherUpdated 2024-09-05
Download on Hugging Face
Parameters3.03B
Context16K
Layers30
Architecturestarcoder2
Smallest quant1.2 GB
Quick answer

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 coding model with 16,384‑token context

Starcoder2 3b is a 3.03B‑parameter transformer decoder trained on 17 programming languages. It uses grouped‑query attention and a sliding window of 4,096 tokens. The model is optimized for code generation but is not an instruction model.

Good at

  • Code generation
  • Fill‑in‑the‑middle tasks
  • Large context handling

Limits

  • Not an instruction model
  • No vision support
  • Requires at least 2 GB VRAM for 8k context

Best for

  • Developing code snippets
  • Debugging code blocks
  • Learning programming patterns

Who it’s for. Engineers and developers who need a lightweight code model for local inference. The model is suitable for environments with limited GPU memory and for tasks that require a large context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 2.0 GB
Fits Get file →
IQ3_XS1.3 GB 2.1 GB
Fits Get file →
Q3_K_S1.4 GB 2.1 GB
Fits Get file →
IQ3_S1.4 GB 2.1 GB
Fits Get file →
IQ3_M1.4 GB 2.2 GB
Fits Get file →
Q3_K_M1.6 GB 2.3 GB
Fits Get file →
IQ4_XS1.7 GB 2.4 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
Q4_K_S1.8 GB 2.5 GB
Fits Get file →
Q4_K_M1.9 GB 2.6 GB
Fits Get file →
Q5_K_S2.1 GB 2.9 GB
Fits Get file →
Q5_K_M2.2 GB 2.9 GB
Fits Get file →
Q6_K2.5 GB 3.2 GB
Fits Get file →
Q8_03.2 GB 4.0 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (file size 1.89 GB, memory 2.6 GB). For 4 GB VRAM use Q3_K_S (1.37 GB, 2.1 GB). For 2 GB VRAM use Q2_K (1.22 GB, 2 GB).

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

Architecturestarcoder2
Parameters3.03B
Layers30
Trained context16,384 tokens
KV cache (fp16)30 KB per token

Source

Quantized bymradermacher
FamilyStarCoder
Downloads (HF)1,868
Last updated2024-09-05

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, IQ3_XS is 1.3 GB, Q3_K_S is 1.4 GB, IQ3_S is 1.4 GB, IQ3_M is 1.4 GB, Q3_K_M is 1.6 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 mradermacher/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, the Q4_K_M quant uses about 2.6 GB at 8k context, fitting within 8 GB VRAM.

Does the model support image inputs?

No, Starcoder2 3b has no vision capability.

What license applies to this model?

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

Other GGUFs of starcoder2-3b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More StarCoder models

All StarCoder →

Other tiny models

All tiny models →