Can I run Skyfall 36B v2 locally?

Yes — the weights are open and TheDrummer publishes both a standard GGUF and an iMatrix-quantized GGUF on Hugging Face, so you can run it in Ollama, LM Studio or any llama.cpp-based tool.

What does it cost to use via API, and how long is the context?

Hosted inference is priced at $0.55 per million input tokens and $0.80 per million output tokens; the context window is 32,768 tokens.

How is this different from plain Mistral Small 2501?

Skyfall 36B v2 is Mistral Small 2501 with additional fine-tuning focused on creative writing, roleplay and storytelling — the base architecture and size are the same, but the output character is meaningfully different for those use cases.

Skyfall 36B V2

2465°

#llm #thedrummer #roleplay #writing #chat #local

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

TheDrummer | 32,768 token context | $0.55/M input, $0.80/M output. Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

How much VRAM do I actually need for local AI?

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Skyfall 36B v2 is TheDrummer's fine-tune of Mistral Small 2501, pushed further with continued training aimed squarely at creative writing and roleplay. At 36B parameters with open weights and GGUF builds available, it sits in a useful gap: smaller than a 70B but, by community accounts, punching above its weight on character work and prose. If you run models locally and care more about narrative quality than benchmark scores, this is worth your time.

Known for

Character roleplay that holds voice and handles nuance better than many larger models
Prose style noticeably above the Mistral Small baseline it was built on
Open weights with GGUF and iMatrix quants ready to run locally
Chain-of-thought and tool-use carried over from the base model
Mistral v7 Tekken chat template recommended for best results

Watch out for

Context window is 32,768 tokens — fine for most sessions, tight for very long documents.
TheDrummer is an independent developer; continuity and support depend on one person.
Licence terms are not detailed publicly; check the Hugging Face repo before any commercial use.

Best for

Prompts to try

Vivid scene, two characters

Write a tense dinner scene between a retired spy and the handler who burned her twenty years ago. They have not spoken since. Show the conversation and what each is thinking but not saying. Keep it under 400 words and let the subtext do the work.

Stay in character hard

You are a gruff, world-weary lighthouse keeper in 1910 who has not spoken to another person in four months. A shipwrecked sailor has just knocked on your door. Respond only as the keeper — no narration, no stage directions, just dialogue. Begin.

Branching story beat

A courier discovers the sealed letter she has been paid to deliver contains evidence that would free a man on death row — but opening it means losing her only client and her reputation. Write the moment she decides, then give me two alternate versions: one where she opens it, one where she does not. 150 words each.

Compare with

Cydonia 24B V4.1
Open-weights model
131,072 token context · $0.30/M input, $0.50/M output
UnslopNemo 12B
Open-weights model
1,024,000 token context · $0.40/M input, $0.40/M output
Aion-3.0-Mini
API-only model
131,072 token context · $0.70/M input, $1.40/M output
MiniMax M2-her
API-only model
65,536 token context · $0.30/M input, $1.20/M output

More text models from thedrummer

Questions people ask

Can I run Skyfall 36B v2 locally?: Yes — the weights are open and TheDrummer publishes both a standard GGUF and an iMatrix-quantized GGUF on Hugging Face, so you can run it in Ollama, LM Studio or any llama.cpp-based tool.
What does it cost to use via API, and how long is the context?: Hosted inference is priced at $0.55 per million input tokens and $0.80 per million output tokens; the context window is 32,768 tokens.
How is this different from plain Mistral Small 2501?: Skyfall 36B v2 is Mistral Small 2501 with additional fine-tuning focused on creative writing, roleplay and storytelling — the base architecture and size are the same, but the output character is meaningfully different for those use cases.

Captain's verdict
A lean, locally-runnable creative model that earns its reputation on character work rather than benchmark tables.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

GLM 5.3 Prime

TEXT / LLM

Llama 4 Scout 17B 16E Instruct

AI Models for Image, Video & Text Generation

Skyfall 36B V2 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm thedrummer roleplay writing chat local

Browse by Model Family