UL

ultravox wip ggml do not use

UltravoxGGUF by ngxsonUpdated 2025-05-20
Download on Hugging Face
Parameters683M
Context—
Layers—
Architectureclip
Smallest quant2.7 GB
Quick answer

ultravox wip ggml do not use needs about 3.5 GB of memory at F32 (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.

ultravox wip ggml do not use is a 683M-parameter Ultravox model in GGUF format, quantized by ngxson. The repository has 1 quant file, from 2.7 GB (F32) to 2.7 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F322.7 GB 3.5 GB
Fits Get file →

What GPU do you need for ultravox wip ggml do not use?

These figures add the file size, an fp16 KV cache at an 8K context window 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 F32 (2.7 GB file, about 3.5 GB in use).

Which ultravox wip ggml do not use quant should you choose?

F32 (2.7 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

Architectureclip
Parameters683M

Source

Quantized byngxson
FamilyUltravox
Licensemit
Downloads (HF)11
Last updated2025-05-20

Frequently asked questions about ultravox wip ggml do not use

How much VRAM does ultravox wip ggml do not use need?

About 3.5 GB at F32 with an 8K context window. That is the 2.7 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 ultravox wip ggml do not use on an 8 GB GPU?

Yes, with F32: the 2.7 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ultravox wip ggml do not use GGUF?

It depends on the quant: F32 is 2.7 GB.

Where can I download ultravox wip ggml do not use GGUF?

The files are on Hugging Face in the ngxson/ultravox-wip-ggml-do-not-use repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ultravox wip ggml do not use use?

Hugging Face lists the license as mit. 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 ngxson

All by ngxson →

Other tiny models

All tiny models →