---
title: Egzakta/Kvark-Sparkle-1.0-27B
url: https://recentmodel.com/models/Egzakta/Kvark-Sparkle-1.0-27B/
status: just landed · new, unvetted
published: 2026-10-19T08:59:21Z
updated: 2026-10-29T11:20:36Z
source: https://huggingface.co/Egzakta/Kvark-Sparkle-1.0-27B
---

# Egzakta/Kvark-Sparkle-1.0-27B

Image text to text model from Egzakta (HF pipeline tag; the card has no one-line description). Dense, 27B params. Context: 256K tokens (config). License: apache-2.0.


- **Org:** Egzakta
- **Released:** 2026-10-19
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 27.4B
- **Architecture:** dense · Qwen3_5ForConditionalGeneration
- **Context:** 262,144 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 2 HF likes · 28 downloads

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~19.9 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.1 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~57.8 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/Egzakta/Kvark-Sparkle-1.0-27B)
- [quant: Egzakta/Kvark-Sparkle-1.0-27B-FP8](https://huggingface.co/Egzakta/Kvark-Sparkle-1.0-27B-FP8)
- [GGUF: Egzakta/Kvark-Sparkle-1.0-27B-GGUF](https://huggingface.co/Egzakta/Kvark-Sparkle-1.0-27B-GGUF)