RO

rocket-3B

RocketGGUF by ddh0Updated 2023-11-23
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant3.1 GB
Quick answer

rocket-3B needs about 6.3 GB of memory at Q8_0 (a 3.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 3.1 GB (Q8_0) to 5.6 GB.

rocket-3B is a 2.8B-parameter Rocket model in GGUF format, quantized by ddh0. Its trained context length is 4K tokens. The repository has 2 quant files, from 3.1 GB (Q8_0) to 5.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.1 GB 4.9 GB
Fits Get file →
—5.6 GB 7.4 GB
Tight Get file →

What GPU do you need for rocket-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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.1 GB file, about 6.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (5.6 GB file, about 8.8 GB in use).

Which rocket-3B quant should you choose?

Q8_0 (3.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestablelm
Parameters2.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byddh0
FamilyRocket
Downloads (HF)14
Last updated2023-11-23

Frequently asked questions about rocket-3B

How much VRAM does rocket-3B need?

About 6.3 GB at Q8_0 with an 8K context window. That is the 3.1 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 rocket-3B on an 8 GB GPU?

Yes, with Q8_0: the 3.1 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rocket-3B GGUF?

It depends on the quant: Q8_0 is 3.1 GB, file is 5.6 GB.

What context length does rocket-3B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download rocket-3B GGUF?

The files are on Hugging Face in the ddh0/rocket-3B-GGUF-fp16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does rocket-3B use?

Hugging Face lists the license as cc-by-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from ddh0

All by ddh0 →

More Rocket models

All Rocket →

Other tiny models

All tiny models →