ST

Bigcode.Starcoder2 3b

StarCoderGGUF by DevQuasar-9Updated 2025-02-23
Download on Hugging Face
Parameters3.03B
Context16K
Layers30
Architecturestarcoder2
Smallest quant1.2 GB
Quick answer

Bigcode.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 11 quants, from 1.2 GB (Q2_K) to 6.1 GB (F16).

StarCoder2 3B – a 3B‑parameter coding model

Bigcode.Starcoder2 3b is a 3.03‑billion parameter model trained on 17 programming languages. It uses a 16,384 token context window and Grouped Query Attention. The model is not an instruction model and is best for code generation tasks.

Good at

  • Code generation
  • Programming language support
  • Large context handling

Limits

  • Not an instruction model
  • No vision support
  • Requires at least 2 GB VRAM for Q2_K

Best for

  • Writing functions
  • Debugging code snippets
  • Generating code examples

Who it’s for. Developers and researchers needing a lightweight coding model. It is suitable for local inference on machines with modest GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 2.0 GB
Fits Get file →
Q3_K_S1.4 GB 2.1 GB
Fits Get file →
Q3_K_M1.6 GB 2.3 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 →
F166.1 GB 6.8 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (1.89 GB) or Q5_K_M (2.18 GB) are good choices. If memory is tighter, Q3_K_M (1.56 GB) or Q3_K_S (1.37 GB) fit. Higher precision models like F16 need 6.06 GB and 6.8 GB RAM at 8 k context.

What GPU do you need for Bigcode.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).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.0 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.1 GB file, about 6.8 GB in use).

Which Bigcode.Starcoder2 3b quant should you choose?

Q4_K_M is the usual starting point for Bigcode.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 byDevQuasar-9
FamilyStarCoder
Downloads (HF)466
Last updated2025-02-23

Frequently asked questions about Bigcode.Starcoder2 3b

How much VRAM does Bigcode.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 Bigcode.Starcoder2 3b on an 8 GB GPU?

Yes, with F16: the 6.1 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bigcode.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_K_S is 1.8 GB, Q4_K_M is 1.9 GB and 5 more.

What context length does Bigcode.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 Bigcode.Starcoder2 3b GGUF?

The files are on Hugging Face in the DevQuasar-9/bigcode.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 Bigcode.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 this model on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantizations will fit within 8 GB VRAM and provide reasonable performance.

Does this model support natural language instructions?

No, it is not an instruction model; commands like "Write a function" do not work well.

What is the context window size?

The model supports up to 16,384 tokens, with a sliding window of 4,096 tokens for attention.

Other GGUFs of starcoder2-3b

Similar models

Browse all →

More from DevQuasar-9

All by DevQuasar-9 →

More StarCoder models

All StarCoder →

Other tiny models

All tiny models →