Cloud Status

Apple

Discord

Google

A roleplaying model that is good at following context, realistically portraying characters, and responding creatively. Performs especially well for its size.

Llama3-based RP and Storytelling model by Hastagaras, with DPO and LORAs applied to reduce cheerfulness and emoji.

First in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Qwen-2 72B Instruct.

Research release of a 104 billion parameter highly performant generative model optimized for reasoning, summarization, and question answering. Command-R supports multilingual generation in 10 languages and has RAG capabilities.

The one and only Space Whale, remastered and requantized in full 32-bit precision. Should be a dramatic improvement over the classic Psyonic Cetacean 20B in terms of creativity and quality of inference.

Version 3.3 of the popular Stheno series, capable of 32K context. A model made for 1-on-1 roleplay, but also able to handle scenarios, RPGs and storywriting. Uncensored during actual roleplay scenarios.

Uncensored Llama2 model that was designed for roleplaying and storytelling and excels at both. The model performs well at other tasks and responds well to changes in the prompt.

Merge between Mythomax and Kimiko. Fine-tuned specifically for roleplay.

Fourth in the Lemon Cookie series of roleplay focused models published by FallenMerick. Chunky Lemon Cookie builds on earlier work to provide a more substantial experience with high emotional intelligence.

Version 3.1 of the Meta Llama base model. This is the instruct variant with 8 billion parameters. Not finetuned for roleplay.

All Systems Operational

Backyard Cloud Models

Fimbulvetr 10.7B

Jamet L3 MK.V Blackroot 8B

Magnum V1 72B

C4ai Command R Plus 104B

Psyonic Cetacean V1 Ultra Quality 20B

L3 Stheno V3.3 32K 8B

Midnight Rose 70B

Mythomax-Kimiko 13B

Chunky Lemon Cookie 11B

Meta Llama 3.1 Instruct 8B