Hemmingway 1
Hemmingway 1 is a text-generation model from the repository Altworld/Hemmingway-1, licensed under cc-by-nc-4.0. Its official model card describes it as built on Qwen/Qwen3.8-27B with 27B parameters, a 262,144-token context, and availability as safetensors weights through the transformers library. It is presented for English chat and creative-writing use, focusing on everyday messages and human-like tone. The card reports comparisons and benchmark placements but provides no hardware requirements or independent verification.
At a glance
- Parameters
- 26.90B
- Architecture
- qwen3_5_text
- Context length
- 262,144
- License
- cc-by-nc-4.0
- Software
- vLLM, Transformers
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Drafting everyday messages such as texts to a landlord, emails, and notes to colleagues
- Assisting with money and administrative writing
- Assisting with work-related writing
- Composing hard asks or messages the user keeps rewriting
- Assisting with persuasive writing or talking someone round
Tradeoffs
- Licensed CC BY-NC 4.0, so commercial use requires a separate agreement
- Model card lists only English language use
- Stated to lose on hostile storytelling and long story turns relative to story models
- Benchmark and comparison claims are from the model card and lack independent verification here
- No hardware requirements, performance figures, or compatibility details are stated or inferred
Ways to run it
vLLM · Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
vllm serve Altworld/Hemmingway-1 --max-model-len 262144Transformers · See official guide
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "Altworld/Hemmingway-1"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", dtype="auto")
messages = [{"role": "user", "content": "Write the text I send my landlord about the broken boiler."}]
ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=512)
print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))Explore its uses
Keep exploring
Bonsai 2 · 27B
A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.
DeepSeek V4.1 Flash
A multimodal reasoning model with a compressed key-value cache, published as open weights.
Qwen3.8-Flash-Next
An experimental open-weight multimodal model with sparse attention and 262K native context.