Can I run ReMM SLERP 13B locally?

Yes, the weights are open and hosted on Hugging Face under Undi95/ReMM-SLERP-L2-13B, so you can download and run them with tools like Ollama or LM Studio.

What does it cost and how long is the context window?

Via API it is priced at $0.35 per million input tokens and $0.65 per million output tokens, with a 6,144-token context window.

How does this differ from the original MythoMax-L2-13B?

ReMM replaces the original MythoMax component models with newer versions of Chronos, Airoboros and Huginn, and uses SLERP merging rather than the original method, making it an updated approximation rather than an exact replica.

ReMM SLERP 13B

1645°

#llm #undi95 #chat #roleplay #writing #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.

undi95 | 6,144 token context | $0.35/M input, $0.65/M output. A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

Guides for this model

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

How much VRAM do I actually need for local AI?

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

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

ReMM SLERP 13B is an open-weights Llama 2 13B merge by Undi95, built as an updated recreation of MythoMax-L2-13B using SLERP and TIES merging across five component models. The combination of Chronos, Airoboros, Nous-Hermes and Huginn leans it toward creative and roleplay use rather than technical tasks. It suits hobbyists who want a capable, locally-runnable chat and storytelling model without a cloud bill.

Known for

SLERP merge technique combining five distinct Llama 2 13B models
Direct lineage from MythoMax, a well-regarded creative writing base
Open weights: runs locally on consumer hardware
Low API cost at $0.35/M input tokens if you prefer hosted inference
Uses standard Alpaca prompt format, broadly supported by local runners

Watch out for

GSM8K score of 9.17 signals weak math; do not rely on it for arithmetic or logic chains.
6,144-token context is short by current standards; long documents will need chunking.
Licence terms follow the component models, including Llama 2's restrictions; check before commercial use.

Best for

Prompts to try

Collaborative story opening

Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: Write the opening two paragraphs of a gothic horror story set in a lighthouse during a storm. Introduce one character and end on an unresolved threat. ### Response:

Character voice exercise

Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: You are a world-weary detective in 1940s Los Angeles. A nervous client has just told you her husband has been missing for three days. Respond in character, asking three questions that reveal your personality. ### Response:

Rewrite for tone

Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: Rewrite the following sentence in three different tones: ominous, comedic, and clinical. Sentence: "The door at the end of the corridor had not been opened in forty years." ### Response:

Compare with

Aion-3.0-Mini
API-only model
131,072 token context · $0.70/M input, $1.40/M output
Weaver (alpha)
API-only model
8,000 token context · $0.40/M input, $0.75/M output
MiniMax M2-her
API-only model
65,536 token context · $0.30/M input, $1.20/M output
GPT-4o-mini (2024-07-18)
API-only model
128,000 token context · $0.15/M input, $0.60/M output

More text models from undi95

Questions people ask

Can I run ReMM SLERP 13B locally?: Yes, the weights are open and hosted on Hugging Face under Undi95/ReMM-SLERP-L2-13B, so you can download and run them with tools like Ollama or LM Studio.
What does it cost and how long is the context window?: Via API it is priced at $0.35 per million input tokens and $0.65 per million output tokens, with a 6,144-token context window.
How does this differ from the original MythoMax-L2-13B?: ReMM replaces the original MythoMax component models with newer versions of Chronos, Airoboros and Huginn, and uses SLERP merging rather than the original method, making it an updated approximation rather than an exact replica.

Captain's verdict
A solid hobbyist merge for local creative writing and roleplay; do not bring it near a spreadsheet.

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

MiMo V2.5

TEXT / LLM

ERNIE 4.5 VL 424B A47B

TEXT / LLM

GLM 4.5 Air

TEXT / LLM

Qwen3 30B A3B Instruct 2507

TEXT / LLM

AI Models for Image, Video & Text Generation

ReMM SLERP 13B 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 undi95 chat roleplay writing local budget

Browse by Model Family