CA

candle whisper

CandleGGUF by lmzUpdated 2023-10-03
Download on Hugging Face
Parameters38M
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

candle whisper needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.0 GB to 0.1 GB.

Candle Whisper: a lightweight 0.0378B model for simple tasks

Candle Whisper is a 0.0378B parameter model. It is available in several GGUF files ranging from 0.02 GB to 0.14 GB. Each file requires about 0.5 GB to 0.7 GB of VRAM at an 8 k context length.

Good at

  • Small footprint
  • Fast inference on modest GPUs
  • Simple text tasks

Limits

  • No context length larger than 8 k
  • No vision or audio support
  • License not specified

Best for

  • Quick prototyping
  • Edge inference
  • Low‑resource environments

Who it’s for. Developers needing a very small model for quick experiments or deployment on devices with limited VRAM. It is suitable for simple text generation or lightweight assistants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.1 GB 0.7 GB
Fits Get file →
—0.1 GB 0.7 GB
Fits Get file →

For 8 GB VRAM, the 0.02 GB files are recommended. If 4 GB VRAM is available, use the 0.04 GB files. For 2 GB VRAM, the 0.13 GB or 0.14 GB files may still fit, but memory usage will be close to the limit. The estimates are approximate.

What GPU do you need for candle whisper?

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 the main file (0.1 GB file, about 0.7 GB in use).

Which candle whisper quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters38M

Source

Quantized bylmz
FamilyCandle
Downloads (HF)3,136
Last updated2023-10-03

Frequently asked questions about candle whisper

How much VRAM does candle whisper need?

About 0.5 GB at its main file with an 8K context window. That is the 0.0 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 candle whisper on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of candle whisper GGUF?

It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, file is 0.1 GB, file is 0.1 GB.

Where can I download candle whisper GGUF?

The files are on Hugging Face in the lmz/candle-whisper repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Candle Whisper on 4 GB VRAM?

Yes, the 0.04 GB GGUF files should fit within 4 GB VRAM, with an estimated 0.5 GB memory usage at 8 k context.

Does Candle Whisper support audio input?

No, the model has no vision or audio support.

What is the context length limit for Candle Whisper?

The model is trained for up to 8 k tokens; larger contexts are not supported.

Similar models

Browse all →

More from lmz

All by lmz →

More Candle models

All Candle →

Other tiny models

All tiny models →