ST

stable-code-instruct-3b

StableGGUF by stabilityaiUpdated 2024-07-10
Download on Hugging Face
Parameters2.8B
Context16K
Layers32
Architecturestablelm
Smallest quant1.7 GB
Quick answer

stable-code-instruct-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 2 quants, from 1.7 GB (Q4_K_M) to 2.0 GB (Q5_K_M).

Stable Code Instruct 3B – 2.8B parameter decoder‑only model tuned for coding

Stable Code Instruct 3B is a 2.8B parameter decoder‑only language model based on the stablelm architecture. It is fine‑tuned from stable-code-3b for coding tasks and supports English language generation.

Good at

  • Coding and software engineering conversations
  • SQL generation and conversation
  • General purpose code instruction

Limits

  • No vision support
  • License requires commercial use check
  • Context limited to 16384 tokens

Best for

  • Writing code snippets
  • Debugging assistance
  • Generating SQL queries

Who it’s for. Developers and programmers who need a lightweight model for code generation and debugging. The model is suitable for integration into IDEs or code assistants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.7 GB 4.9 GB
Fits Get file →
Q5_K_M2.0 GB 5.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.71 GB file, ~4.9 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (1.99 GB file, ~5.2 GB memory) is also suitable. Memory estimates are approximate.

What GPU do you need for stable-code-instruct-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 Q5_K_M (2.0 GB file, about 5.2 GB in use).

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

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

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 bystabilityai
FamilyStable
Licenseother
Downloads (HF)2,419
Last updated2024-07-10

Frequently asked questions about stable-code-instruct-3b

How much VRAM does stable-code-instruct-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-instruct-3b on an 8 GB GPU?

Yes, with Q5_K_M: the 2.0 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q4_K_M is 1.7 GB, Q5_K_M is 2.0 GB.

What context length does stable-code-instruct-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-instruct-3b GGUF?

The files are on Hugging Face in the stabilityai/stable-code-instruct-3b 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-instruct-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 Instruct 3B on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires about 4.9 GB of VRAM at 8 k context, which fits within an 8 GB GPU.

Does the model support multiple languages?

The model is trained for English only; no other languages are supported.

Is there a commercial license?

Commercial use requires checking the StabilityAI Community License and the commercial license at https://stability.ai/license.

Similar models

Browse all →

More from stabilityai

All by stabilityai →

More Stable models

All Stable →

Other tiny models

All tiny models →