---
title: zerofata/G4-LuneLight-31B
url: https://recentmodel.com/models/zerofata/G4-LuneLight-31B/
status: just landed · new, unvetted
published: 2026-10-24T01:53:53Z
updated: 2026-10-26T11:26:59Z
source: https://huggingface.co/zerofata/G4-LuneLight-31B
---

# zerofata/G4-LuneLight-31B

Dense, 31B params. Context: 256K tokens (config). License: apache-2.0.


- **Org:** zerofata
- **Released:** 2026-10-24
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 31.3B
- **Architecture:** dense · Gemma4ForConditionalGeneration
- **Context:** 262,144 tokens
- **Signal:** 10 HF likes · 29 downloads

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~27.8 GB: 32GB GPU (5090), Mac 48GB
- Q8 ~41.7 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~70.5 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/zerofata/G4-LuneLight-31B)
- [GGUF: zerofata/G4-LuneLight-31B-GGUF](https://huggingface.co/zerofata/G4-LuneLight-31B-GGUF)