SE

Severian_Jamba-UltraInteract-Instruct-1B

SeverianGGUF by SeverianUpdated 2024-05-26
Download on Hugging Face
Parameters1.02B
Context256K
Layers8
Architecturejamba
Smallest quant2.1 GB
Quick answer

Severian_Jamba-UltraInteract-Instruct-1B needs about 2.8 GB of memory at BF16 (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

Severian_Jamba-UltraInteract-Instruct-1B is a 1.02B-parameter Severian model in GGUF format, quantized by Severian. Its trained context length is 256K tokens. The repository has 1 quant file, from 2.1 GB (BF16) to 2.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF162.1 GB 2.8 GB
Fits Get file →

What GPU do you need for Severian_Jamba-UltraInteract-Instruct-1B?

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 BF16 (2.1 GB file, about 2.8 GB in use).

Which Severian_Jamba-UltraInteract-Instruct-1B quant should you choose?

BF16 (2.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturejamba
Parameters1.02B (approximate, mixture of experts)
Layers8
Trained context262,144 tokens
KV cache (fp16)32 KB per token

Source

Quantized bySeverian
FamilySeverian
Licenseapache-2.0
Downloads (HF)24
Last updated2024-05-26

Frequently asked questions about Severian_Jamba-UltraInteract-Instruct-1B

How much VRAM does Severian_Jamba-UltraInteract-Instruct-1B need?

About 2.8 GB at BF16 with an 8K context window. That is the 2.1 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 Severian_Jamba-UltraInteract-Instruct-1B on an 8 GB GPU?

Yes, with BF16: the 2.1 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Severian_Jamba-UltraInteract-Instruct-1B GGUF?

It depends on the quant: BF16 is 2.1 GB.

What context length does Severian_Jamba-UltraInteract-Instruct-1B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download Severian_Jamba-UltraInteract-Instruct-1B GGUF?

The files are on Hugging Face in the Severian/Jamba-UltraInteract-Instruct-1B-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 Severian_Jamba-UltraInteract-Instruct-1B use?

Hugging Face lists the license as apache-2.0. 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 Severian

All by Severian →

More Severian models

All Severian →

Other tiny models

All tiny models →