---
title: HemmingwayAI/Hemmingway-1.5
url: https://recentmodel.com/models/HemmingwayAI/Hemmingway-1.5/
status: just landed · new, unvetted
published: 2026-10-24T21:01:56Z
updated: 2026-10-24T23:23:29Z
source: https://huggingface.co/HemmingwayAI/Hemmingway-1.5
---

# HemmingwayAI/Hemmingway-1.5

We gave Hemmingway-1.5 and the biggest models the same 80 everyday asks, the asks from CommunicationBench, and ran every answer through the same detectors. Dense, 27B params. Context: 256K tokens (config). License: cc-by-nc-4.0.


- **Org:** HemmingwayAI
- **Released:** 2026-10-24
- **Status:** just landed · new, unvetted
- **License:** cc-by-nc-4.0 (restricted)
- **Parameters:** 26.9B
- **Architecture:** dense · Qwen3_5ForCausalLM
- **Context:** 262,144 tokens
- **Task:** text-generation · text
- **Signal:** 2 HF likes · 321 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 ~57.7 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/HemmingwayAI/Hemmingway-1.5)