Featherless
DeepHermes-3-Mistral-24B-PreviewNousResearch
Start Chat
24B Params FP8 Open Weights Inference Available

DeepHermes 3 - Mistral 24B Preview by Nous Research is a 24 billion parameter language model with a 32768 token context length, uniquely designed to unify both intuitive and long chain-of-thought reasoning modes. This model excels at complex problem-solving by allowing users to toggle deep reasoning via a system prompt, alongside improved LLM annotation, judgment, and function calling capabilities. It is optimized for advanced agentic tasks, multi-turn conversations, and enhanced user steerability.

Loading preview...

Parameters:24BContext length:32kArchitecture:TransformerPrecision:FP8Quantized variants:AvailableLast updated:March 2025
0.0M
0.1K

Model tree for

NousResearch/DeepHermes-3-Mistral-24B-Preview
Popular Sampler Settings

Most commonly used values from Featherless users

temperature

This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.

–

top_p

This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.

–

top_k

This limits the number of top tokens to consider. Set to -1 to consider all tokens.

–

frequency_penalty

This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.

–

presence_penalty

This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.

–

repetition_penalty

This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.

–

min_p

This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.

–