Model library / HemmingwayAI
Hemmingway-1.5 is a 26.9 B open-weight language model aimed at everyday writing tasks.
Parameters in total
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
Hemmingway-1.5 is a Qwen-3.5-based causal language model released by HemmingwayAI. The publisher positions it for product descriptions, blog posts, emails, stories, speeches, comments and rewriting existing AI-generated text to appear human-written. It is provided with an OpenAI-compatible API and desktop apps for Mac, Windows and Android.
The model contains 26.9 billion parameters and supports a context window of 262,144 tokens. Weights are stored in bfloat16 format and the architecture has no expert layers. It is distributed under a CC-BY-NC-4.0 licence, allowing free personal, research and non-commercial use with attribution; commercial use requires a separate agreement.
Specification
| Repository | HemmingwayAI/Hemmingway-1.5 |
| Publisher | HemmingwayAI |
| Published | 24 October 2026 |
| Architecture | Qwen3_5ForCausalLM |
| Model type | qwen3_5_text |
| Parameters | 26,895,998,464 |
| Layers | 64 |
| Hidden size | 5,120 |
| Attention heads | 24, 4 key/value heads |
| Context length | 262,144 tokens |
| Vocabulary | 248,320 tokens |
| Weight format | bfloat16 |
| Licence | cc-by-nc-4.0 |
| Base model | HemmingwayAI/Hemmingway-1 |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 50.1 GiB | Full precision as released |
| fp8 | 25.0 GiB | 8-bit, near-lossless on most models |
| int4 | 12.5 GiB | 4-bit, smallest footprint |
The cache costs 256 KiB per token at 16-bit, so the full 262,144-token context of one request needs about 64.0 GiB. Concurrency multiplies that number, not the weights.
Hardware
At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.
| GPU | Cards needed | Free for cache | Context it holds |
|---|---|---|---|
| RTX 4090 24GB | 4 | 25.5 GiB | about 104,494 tokens |
| RTX 5090 32GB | 2 | 1.7 GiB | about 7,009 tokens |
| L40S 48GB | 2 | 30.5 GiB | about 124,974 tokens |
| A100 80GB | 1 | 18.6 GiB | about 76,231 tokens |
| H100 80GB | 1 | 18.6 GiB | about 76,231 tokens |
| RTX PRO 6000 96GB | 1 | 33.0 GiB | about 135,214 tokens |
| H200 141GB | 1 | 73.5 GiB | the full 262,144 tokens |
Serving
A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.
vllm serve HemmingwayAI/Hemmingway-1.5 \ --max-model-len 102400 \ --gpu-memory-utilization 0.90
Questions
The weights take about 51 GiB at the released precision. That fits on one A100 80GB, which leaves roughly 19 GiB for the key-value cache.
The repository declares cc-by-nc-4.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.
The configuration allows 262,144 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.
This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email hello@aiqre.com with the model name and roughly what volume you expect.
Also in the library
Hemmingway-1 is a 27 billion-parameter open-weight model from HemmingwayAI designed for everyday English writing tasks.
Nanbeige4.3-33B is a 33.1 billion-parameter Llama-style causal model released by Nanbeige for high-capacity agentic tasks and tea…
Nanbeige4.3-33B-Base is a 33.1-billion-parameter Llama-style causal language model released by Nanbeige under Apache-2.0.
Flint is a 39.8 billion-parameter language model for coding agents, using about 2.5 billion active parameters per token.
Hosting
Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.