---
title: LessThanThreeAI/Gemma-4-31B-Humanlike-Chat
url: https://recentmodel.com/models/LessThanThreeAI/Gemma-4-31B-Humanlike-Chat/
status: just landed · new, unvetted
published: 2026-10-23T11:14:16Z
updated: 2026-10-30T11:19:53Z
source: https://huggingface.co/LessThanThreeAI/Gemma-4-31B-Humanlike-Chat
---

# LessThanThreeAI/Gemma-4-31B-Humanlike-Chat

Text generation model from LessThanThreeAI (HF pipeline tag; the card has no one-line description). Dense, 31B params. Context: 256K tokens (config). License: apache-2.0.


- **Org:** LessThanThreeAI
- **Released:** 2026-10-23
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 31.3B
- **Architecture:** dense · Gemma4ForConditionalGeneration
- **Context:** 262,144 tokens
- **Task:** text-generation · text
- **Signal:** 4 HF likes · 0 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 ~71.5 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/LessThanThreeAI/Gemma-4-31B-Humanlike-Chat)
- [Ollama](https://ollama.com/library/gemma4)
- [quant: LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8](https://huggingface.co/LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8)
- [quant: LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-GPTQ-Int4](https://huggingface.co/LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-GPTQ-Int4)