Weaver (alpha)
4960°
Run this model
Offers / Ads
Mancer | 8,000 token context | $0.40/M input, $0.75/M output. An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.
Guides for this model
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
Open weights vs open source vs API-only: what you are actually allowed to do
Captain's notes
Notes from 2026-10-13
Weaver is a closed-weights model from Mancer built specifically for roleplay and narrative writing, aiming to replicate the verbose, descriptive style associated with Claude. Mancer is upfront that coherence and memory fall short of that benchmark, so treat it as a creative writing assistant rather than a general-purpose model. It suits writers who want long, atmospheric prose and can tolerate occasional drift.
Known for
- Verbose, descriptive output tuned for narrative and roleplay contexts
- Priced low: $0.40 per million input tokens, $0.75 per million output
- Targets Claude-style prose style without requiring Claude access
- Designed by Mancer, a provider focused on creative and roleplay use cases
Watch out for
- Coherence and memory are acknowledged as weaker than Claude; long scenes may drift.
- Closed weights, API-only — you cannot run this locally.
- 8,000-token context is tight for extended narrative sessions.
Prompts to try
Open a gothic scene
Write the opening three paragraphs of a gothic horror story set in a crumbling Victorian manor during a thunderstorm. A lone archivist has just discovered a locked iron door behind a bookcase. Focus on atmosphere, sensory detail and a creeping sense of dread. Do not resolve the tension.
NPC dialogue in character
You are a weary, sardonic innkeeper in a fantasy city who has seen too many adventurers come and go. A traveller sits down and asks you what trouble has been brewing in town lately. Respond in character, with colour and a hint of dark humour, for about three paragraphs.
Expand a sparse scene
Take this bare scene note and expand it into a full descriptive passage of around 200 words: a mercenary returns to her childhood village after ten years away and finds it abandoned, the well dry, the doors left open as if everyone left in a hurry.
Compare with
- Cydonia 24B V4.1Open-weights model131,072 token context · $0.30/M input, $0.50/M output
- Llama 3 8B LunarisOpen-weights model8,192 token context · $0.04/M input, $0.05/M output
- MythoMax 13BOpen-weights model8,192 token context · $0.08/M input, $0.11/M output
- L3 8B Lunaris v1 TurboOpen-weights model8,192 token context · $0.04/M input, $0.05/M output
More text models from mancer
Questions people ask
- Can I run Weaver locally?
- No. Weaver is a closed-weights, API-only model hosted by Mancer; there is no public repository and no way to download the weights.
- What does Weaver cost and how much context does it have?
- Mancer charges $0.40 per million input tokens and $0.75 per million output tokens, with an 8,000-token context window.
- How does Weaver compare to Claude for creative writing?
- Mancer built Weaver to mimic Claude's verbose, descriptive prose style, but explicitly notes that coherence and memory do not match Claude — useful for atmosphere, less reliable for complex, long-running narratives.
Captain's verdictA cheap, honest-about-its-limits prose generator — fine for atmospheric roleplay, not a Claude replacement.
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.
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.
Weaver (alpha) 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.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153