---
title: SubMaroon/Kitchoon-V3-26B-A4B
url: https://recentmodel.com/models/SubMaroon/Kitchoon-V3-26B-A4B/
status: just landed · new, unvetted
published: 2026-10-20T21:47:53Z
updated: 2026-10-22T23:27:46Z
source: https://huggingface.co/SubMaroon/Kitchoon-V3-26B-A4B
---

# SubMaroon/Kitchoon-V3-26B-A4B

The Kitchoon series is designed as an RP- and ERP-oriented model, focusing on character development and featuring a neutral writing style. Mixture-of-experts, 26B total, 4B active (128 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0.


- **Org:** SubMaroon
- **Released:** 2026-10-20
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 25.8B total, 4.0B active
- **Architecture:** MoE · 128 experts, 8/token · Gemma4ForConditionalGeneration
- **Context:** 262,144 tokens
- **Signal:** 9 HF likes · 113 downloads

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~19.8 GB: 24GB GPU (3090 / 4090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~29.9 GB: 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), Arc B70 32GB, Mac 48GB, Mac 64GB (M1 Max)
- FP16 ~54.6 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, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/SubMaroon/Kitchoon-V3-26B-A4B)