ST

stable-code-3b

StableGGUF by mradermacherUpdated 2024-07-13
Download on Hugging Face
Parameters2.8B
Context16K
Layers32
Architecturestablelm
Smallest quant1.1 GB
Quick answer

stable-code-3b needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.1 GB (Q2_K) to 5.6 GB (F16).

Stable-code-3b: 2.8B parameter code model with long context

Stable-code-3b is a 2.8B parameter decoder-only language model trained on 1.3 trillion tokens. It supports 18 programming languages and a maximum context length of 16384 tokens. The model is available in multiple GGUF quantizations.

Good at

  • Coding in 18 languages
  • Long context generation
  • Fill in Middle capability

Limits

  • No vision support
  • License requires commercial check
  • Large memory for higher quants

Best for

  • Code generation tasks
  • Debugging assistance
  • Educational coding examples

Who it’s for. Developers and researchers needing a compact code model with extended context. The model is suitable for local inference on machines with moderate GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 4.3 GB
Fits Get file →
IQ3_XS1.2 GB 4.4 GB
Fits Get file →
IQ3_S1.3 GB 4.4 GB
Fits Get file →
Q3_K_S1.3 GB 4.4 GB
Fits Get file →
IQ3_M1.3 GB 4.5 GB
Fits Get file →
Q3_K_M1.4 GB 4.6 GB
Fits Get file →
Q3_K_L1.5 GB 4.7 GB
Fits Get file →
IQ4_XS1.5 GB 4.7 GB
Fits Get file →
Q4_K_S1.6 GB 4.8 GB
Fits Get file →
Q4_K_M1.7 GB 4.9 GB
Fits Get file →
Q5_K_S1.9 GB 5.1 GB
Fits Get file →
Q5_K_M2.0 GB 5.2 GB
Fits Get file →
Q6_K2.3 GB 5.5 GB
Fits Get file →
Q8_03.0 GB 6.2 GB
Fits Get file →
F165.6 GB 8.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (1.71 GB file, ~4.9 GB memory). For 12 GB VRAM, Q5_K_M (1.99 GB file, ~5.2 GB memory). For 16 GB VRAM, Q6_K (2.3 GB file, ~5.5 GB memory).

What GPU do you need for stable-code-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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q6_K (2.3 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.8 GB in use).

Which stable-code-3b quant should you choose?

Q4_K_M is the usual starting point for stable-code-3b: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 3.0 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 1.1 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

Architecturestablelm
Parameters2.8B
Layers32
Trained context16,384 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyStable
Licenseother
Downloads (HF)2,579
Last updated2024-07-13

Frequently asked questions about stable-code-3b

How much VRAM does stable-code-3b need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 stable-code-3b on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of stable-code-3b GGUF?

It depends on the quant: Q2_K is 1.1 GB, IQ3_XS is 1.2 GB, IQ3_S is 1.3 GB, Q3_K_S is 1.3 GB, IQ3_M is 1.3 GB, Q3_K_M is 1.4 GB and 9 more.

What context length does stable-code-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 2.7 GB at 8K and 5.4 GB at 16K.

Where can I download stable-code-3b GGUF?

The files are on Hugging Face in the mradermacher/stable-code-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 stable-code-3b use?

Hugging Face lists the license as other. 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 stable-code-3b on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 4.9 GB of VRAM at 8 k context.

Does stable-code-3b support image inputs?

No, the model only processes text and code.

What is the maximum context length of stable-code-3b?

The model is trained with a context length of 16384 tokens.

Other GGUFs of stable-code-3b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Stable models

All Stable →

Other tiny models

All tiny models →