SP

Spark

SparkGGUF by ZuellniUpdated 2025-03-18
Download on Hugging Face
Parameters507M
Context32K
Layers24
Architectureqwen2
Smallest quant0.4 GB
Quick answer

Spark needs about 1.1 GB of memory at Q6_K (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.4 GB (Q4_K) to 2.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

Spark is a 507M-parameter Spark model in GGUF format, quantized by Zuellni. Its trained context length is 32K tokens. The repository has 6 quant files, from 0.4 GB (Q4_K) to 2.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.4 GB 1.0 GB
Fits Get file →
Q5_K0.4 GB 1.0 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
BF161.0 GB 1.6 GB
Fits Get file →
—2.0 GB 2.6 GB
Fits Get file →

What GPU do you need for Spark?

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 the main file (2.0 GB file, about 2.6 GB in use).

Which Spark quant should you choose?

Q6_K (0.5 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_K at 0.4 GB, with the quality trade-offs that come with fewer bits. 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

Architectureqwen2
Parameters507M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized byZuellni
FamilySpark
Downloads (HF)72
Last updated2025-03-18

Frequently asked questions about Spark

How much VRAM does Spark need?

About 1.1 GB at Q6_K with an 8K context window. That is the 0.5 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 Spark on an 8 GB GPU?

Yes, with the smaller files: the 2.0 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Spark GGUF?

It depends on the quant: Q4_K is 0.4 GB, Q5_K is 0.4 GB, Q6_K is 0.5 GB, Q8_0 is 0.5 GB, BF16 is 1.0 GB, file is 2.0 GB.

What context length does Spark support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download Spark GGUF?

The files are on Hugging Face in the Zuellni/Spark-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 Spark-TTS-0.5B

Similar models

Browse all →

More from Zuellni

All by Zuellni →

More Spark models

All Spark →

Other tiny models

All tiny models →