CA

candela spark 35m

CandelaGGUF by UmitViceUpdated 2026-10-23
Download on Hugging Face
Parameters35M
Context1K
Layers12
Architecturegemma3
Smallest quant0.0 GB
Quick answer

candela spark 35m needs about 0.6 GB of memory at Q4_1 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

candela spark 35m is a 35M-parameter Candela model in GGUF format, quantized by UmitVice. Its trained context length is 1K tokens. The repository has 1 quant file, from 0.0 GB (Q4_1) to 0.0 GB (Q4_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_10.0 GB 0.5 GB
Fits Get file →

What GPU do you need for candela spark 35m?

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 Q4_1 (0.0 GB file, about 0.6 GB in use).

Which candela spark 35m quant should you choose?

Q4_1 (0.0 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

Architecturegemma3
Parameters35M
Layers12
Trained context1,024 tokens
KV cache (fp16)6 KB per token

Source

Quantized byUmitVice
FamilyCandela
Licenseapache-2.0
Downloads (HF)87
Last updated2026-10-23

Frequently asked questions about candela spark 35m

How much VRAM does candela spark 35m need?

About 0.6 GB at Q4_1 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 candela spark 35m on an 8 GB GPU?

Yes, with Q4_1: the 0.0 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of candela spark 35m GGUF?

It depends on the quant: Q4_1 is 0.0 GB.

What context length does candela spark 35m support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.

Where can I download candela spark 35m GGUF?

The files are on Hugging Face in the UmitVice/candela-spark-35m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does candela spark 35m 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 UmitVice

All by UmitVice →

Other tiny models

All tiny models →