TU

Tulu 3.1 8B SuperNova

TuluGGUF by bunnycoreUpdated 2024-11-23
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

Tulu 3.1 8B SuperNova needs about 6.0 GB of memory at IQ4_XS (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Tulu 3.1 8B SuperNova is a 8.03B-parameter Tulu model in GGUF format, quantized by bunnycore. Its trained context length is 128K tokens. The repository has 1 quant file, from 4.4 GB (IQ4_XS) to 4.4 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS4.4 GB 6.0 GB
Fits Get file →

What GPU do you need for Tulu 3.1 8B SuperNova?

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 IQ4_XS (4.4 GB file, about 6.0 GB in use).

Which Tulu 3.1 8B SuperNova quant should you choose?

IQ4_XS (4.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybunnycore
FamilyTulu
Downloads (HF)13
Last updated2024-11-23

Frequently asked questions about Tulu 3.1 8B SuperNova

How much VRAM does Tulu 3.1 8B SuperNova need?

About 6.0 GB at IQ4_XS with an 8K context window. That is the 4.4 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 Tulu 3.1 8B SuperNova on an 8 GB GPU?

Yes, with IQ4_XS: the 4.4 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tulu 3.1 8B SuperNova GGUF?

It depends on the quant: IQ4_XS is 4.4 GB.

What context length does Tulu 3.1 8B SuperNova support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Tulu 3.1 8B SuperNova GGUF?

The files are on Hugging Face in the bunnycore/Tulu-3.1-8B-SuperNova-Smart-IQ4_XS-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Tulu-3.1-8B-SuperNova-Smart

Similar models

Browse all →

More from bunnycore

All by bunnycore →

More Tulu models

All Tulu →

Other small models

All small models →