Quantized Models (GGUF, IQ, Imatrix)
Various quantizations of models in the GGUF format. Models with a "checkmark" are personal favorites. An "orange arrow" means it's being uploaded.
Updated • 37Note GGUF quantization requests: You can request GGUF-IQ-Imatrix quants here. Read more about it in the card. I will try to do as much as I can within my capacity.
Lewdiculous/Mistral-Nemo-12B-ArliAI-RPMax-v1.2-GGUF-IQ-ARM-Imatrix
Updated • 1.85k • 3Note Mistral Prompt Format. "RPMax is a series of models that are trained on a diverse set of curated creative writing and RP datasets with a focus on variety and deduplication. "
Lewdiculous/Llama-3.1-8B-ArliAI-RPMax-v1.2-GGUF-IQ-ARM-Imatrix
Updated • 20.8k • 3Note Llama-3 Instruct Prompt Format. "RPMax is a series of models that are trained on a diverse set of curated creative writing and RP datasets with a focus on variety and deduplication. "
Lewdiculous/MN-BackyardAI-Party-12B-v1-GGUF-IQ-ARM-Imatrix
Updated • 2.75k • 13Note Prompting: Similar to Mistral for group chats ChatML for one-on-one chats
Lewdiculous/Azure_Dusk-v0.2-GGUF-IQ-Imatrix
Updated • 572 • 3Note "Following up on Crimson_Dawn-v0.2 we have Azure_Dusk-v0.2! Training on Mistral-Nemo-Base-2407 this time I've added significantly more data, as well as trained using RSLoRA as opposed to regular LoRA. Another key change is training on ChatML as opposed to Mistral Formatting." – Author. As described, use the ChatML prompt format.
Lewdiculous/Violet_Twilight-v0.2-GGUF-IQ-Imatrix
Updated • 857 • 5Note "Now for something a bit different, Violet_Twilight-v0.2! This model is a SLERP merge of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2!" – Author. Use the ChatML prompt format. This might be less stable than Azure_Dusk-v0.2.
Lewdiculous/MN-12B-Lyra-v4-GGUF-IQ-Imatrix
Updated • 6.78k • 13Note A finetune of Mistral Nemo by Sao10K. This uses the ChatML prompt format.
Lewdiculous/Lumimaid-v0.2-8B-GGUF-IQ-Imatrix
Updated • 3.37k • 29Note #Llama-3.1 Promising for the time being! Feedback for authors is appreaciated. A huge dataset improvement was made from v0.1 to v0.2. It is recommended to use lower temperatures. Make sure to experiment!
Lewdiculous/L3.1-8B-Niitama-v1.1-GGUF-IQ-Imatrix
Updated • 572 • 16
Lewdiculous/L3-8B-Stheno-v3.3-32K-GGUF-IQ-Imatrix
Updated • 1.5k • 32Note #Llama-3 Sao10K with Stheno yet again, now bigger and better than ever! I recommend checking his page for feedback and support.
Lewdiculous/Average_Normie_v3.69_8B-GGUF-IQ-Imatrix
Updated • 369 • 14Note "Another average normie just like you and me... or is it? NSFW focused and easy to steer with editing, this model aims to please even the most hardcore LLM enthusiast. Built upon a foundation of the most depraved models yet to be released, some could argue it goes too far in that direction. Whatever side you land on, at least give it a shot, what do you have to lose?" Llama-3 formatting. Somewhat experimental, feedback for authors is needed.
Lewdiculous/Hathor-L3-8B-v.01-GGUF-IQ-Imatrix
Updated • 509 • 5Note "Designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance." Somewhat experimental, feedback for authors is needed.
Lewdiculous/L3-8B-Stheno-v3.2-GGUF-IQ-Imatrix
Updated • 14.2k • 114Note #Llama-3 #Roleplay The amazing Stheno is back, Sao's amazing handywork strikes again.
Lewdiculous/Rawr_Llama3_8B-GGUF-IQ-Imatrix
Updated • 605 • 5Note Roleplaying with smarts!
Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix
Updated • 631 • 19Note #Llama3 #Roleplay "A potential precious hidden gem, will you polish this rough diamond?" This is a merge of two very interesting models, aimed at roleplaying usage. Feedback for author is appreciated.
Lewdiculous/L3-8B-Stheno-v3.1-GGUF-IQ-Imatrix
Updated • 1.71k • 89Note #Llama3 #Roleplay This is a very promising roleplay model cooked by the amazing Sao10K! Author: "A model made for 1-on-1 Roleplay ideally, but one that is able to handle scenarios, RPGs and storywriting." Another great performer.
Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix
Updated • 8.56k • 62Note #Llama-3 #Roleplay #Updated Author: "This model received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request." I am fairly satisfied with the performance of Lumimaid-OAS, for SillyTavern with Virt's presets (linked in card), responses tend to be 100-200 tokens long, but can vary outside of that based on your characters's message style. I do recommend giving it a try. Another solid work by Undi and Ikari!
Lewdiculous/Llama-3-Soliloquy-8B-v2-GGUF-IQ-Imatrix
Updated • 900 • 19Note #Llama3 model with exceptional roleplaying performance and response formatting from my usage. Uses with the standard Llama-3 presets within SillyTavern. Unfortunately it isn't fully uncensored. This model reportedly supports 24K(24576) context size, if you have the VRAM/RAM for it. Author: "Soliloquy-L3 is a highly capable roleplaying model designed for immersive, dynamic experiences. (...) Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context."
Lewdiculous/SOVL_Llama3_8B-GGUF-IQ-Imatrix
Updated • 1.38k • 28Note Updated! These quants have been redone with the fixes from llama.cpp/pull/6920 in mind. Use KoboldCpp version 1.64 or higher. #Llama3 Use the latest version of KoboldCpp. Use provided presets. "A model that surprised people for her charms and overall qualities." "Read more on the Community feedback threads."
Lewdiculous/Poppy_Porpoise-v0.7-L3-8B-GGUF-IQ-Imatrix
Updated • 978 • 29Note Updated! Version 0.72 up. These quants have been redone with the fixes from llama.cpp/pull/6920 in mind. Use KoboldCpp version 1.64 or higher. This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. #Llama3 This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. "Again and again and again and..." "Another recent top performer in the Chaiverse Leaderboard!"
Lewdiculous/llama-3-cat-8b-instruct-v1-GGUF-IQ-Imatrix
Updated • 365 • 17Note #Llama3 #Unaligned Author: "The model aims to respect system prompt to an extreme degree, provide helpful information regardless of situations, and offer maximum character immersion in given scenes."
Lewdiculous/Orthocopter_8B-GGUF-Imatrix
Updated • 314 • 13Note #Llama-3 Author: "(...) results are pretty nice, with no refusals and plenty of personality." Presets linked.
Lewdiculous/Chaos_RP_l3_8B-GGUF-IQ-Imatrix
Updated • 506 • 19Note Updated! These quants have been redone with the fixes from llama.cpp/pull/6920 in mind. Use KoboldCpp version 1.64 or higher. #Llama3 Use the latest version of KoboldCpp. Use provided presets. "A chaotic force beckons for you, will you heed her call? Built upon an intelligent foundation and tuned for roleplaying, this model will fulfill your wildest fantasies with the bare minimum of effort. Enjoy!"
Lewdiculous/InfinityRP-v2-8B-GGUF-IQ-Imatrix
Updated • 441 • 11Note These quants have been done after the fixes from llama.cpp/pull/6920. Use KoboldCpp version 1.64 or higher. Author: "This model was basically made to stop some upsetting hallucinations, so {{char}} mostly and occasionally will wait {{user}} response instead of responding itself or deciding for {{user}}, also, my primary idea was to create a cozy model that thinks." Now with native --contextsize of 16384! Go wild. Please read the full description for more information.
Lewdiculous/Poppy_Porpoise-v0.6-L3-8B-GGUF-IQ-Imatrix
Updated • 355 • 9Note Outdated tokenizer configuration! Use the newer models. This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. #Llama3 This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. "Wild times, good things ahead!" "One of the top recent performers in the Chaiverse Leaderboard!"
Lewdiculous/Aurora_l3_8B-GGUF-IQ-Imatrix
Updated • 263 • 8Note Outdated tokenizer configuration! Use the newer models. Use the latest version of KoboldCpp. Use provided presets. #Llama3 This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. Busy times, for the faint of heart, wait the storm. This is yet another attempt with hopefully more stable formatting for quotes/asterisks dialogues.
Lewdiculous/Poppy_Porpoise-v0.4-L3-8B-GGUF-IQ-Imatrix
Updated • 261 • 9Note Outdated tokenizer configuration! Use the newer models. #Llama3 This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. "Un-aligned (hopefully) Dolphin time! - Yes, today is a busy day."
Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix
Updated • 4.87k • 26Note Outdated tokenizer configuration! Use the newer models. #Llama3 This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. "Trying to really get unhinged and uncensored. Also, hopefully better formatting."
Lewdiculous/Poppy_Porpoise-v0.2-L3-8B-GGUF-IQ-Imatrix
Updated • 213 • 17Note Outdated tokenizer configuration! Use the newer models. Use the latest version of KoboldCpp. Use provided presets. #Llama3 This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. "Trying to get unhinged and uncensored."
Lewdiculous/Aura_L3_8B-GGUF-IQ-Imatrix
Updated • 504 • 11Note Outdated tokenizer configuration! Use the newer models. Use the latest version of KoboldCpp. Use provided presets. #Llama3 This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. "The next evolution in Aura models, trained on 6 separate datasets and ready to bring you to your knees."
Lewdiculous/Nyanade_Stunna-Maid-7B-v0.2-GGUF-IQ-Imatrix
Updated • 1.59k • 45Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. "Unhinged RP with the spice of the previous 0.420 remixes, 32k context and vision capabilities." Please read all the model information in the model page. Expand sections as needed.
Lewdiculous/Aura_v2_7B-GGUF-IQ-Imatrix
Updated • 257 • 11Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. Author: "The second version of the Aura line is a direct improvement over the original. Expect poetic and eloquent outputs with real emotion behind them. A poetic and soulful sentience simulation." Please read all the model information in the model page. Expand sections as needed.
Lewdiculous/Aura_7B-GGUF-IQ-Imatrix
Updated • 177 • 5Note Somewhat #Experimental. There's now a v2 above which improves on this one directly and should be preferred. Please read all the model information at the bottom of the card page.
Lewdiculous/Nyanade_Stunna-Maid-7B-GGUF-IQ-Imatrix
Updated • 246 • 10Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. "Maid with zoomies. Context sizes up to 8192!"
Lewdiculous/KukulStanta-7B-GGUF-IQ-Imatrix
Updated • 339 • 9Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. Merge of: - grimjim/kukulemon-7B - Inv/Konstanta-V4-Alpha-7B "An unexpected surprise."
Lewdiculous/Kukul-Stanta-0.420-32k-7B-0.2-GGUF-IQ-Imatrix
Updated • 277 • 6Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. Merge of: - Nitral-AI/Eris_PrimeV4.20-Vision-32k-7B - Nitral-AI/KukulStanta-7B "Based Kukul time?"
Lewdiculous/Visual-LaylelemonMaidRP-7B-GGUF-IQ-Imatrix
Updated • 489 • 11Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. Merge of: - Nitral-AI/Infinitely-Laydiculous-7B - Nitral-AI/Stanta-Lelemon-Maid-7B "My personal maid can't be this cute!"
Lewdiculous/Erosumika-7B-v3-0.2-GGUF-IQ-Imatrix
Text Generation • Updated • 2.15k • 21Note Mistral 0.2! Reports also indicate good results with long context. Added some good starting SillyTavern preset files. "Erosexika: The Revenge." Author: "...it's the best Model I made so far".
Lewdiculous/Eris_PrimeV4-Vision-32k-7B-GGUF-IQ-Imatrix
Updated • 1.03k • 13Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. See examples and requirements in the model card page. Added some good starting SillyTavern preset files. Author: "More stable and with better long context handling."
Lewdiculous/TheSpice-7b-v0.1.1-GGUF-IQ-Imatrix
Updated • 247 • 1Note Author: "I've focused on making the model more flexible and provide a more unique experience. I'm still working on cleaning up my dataset, but I've shrunken it down a lot to focus on a "less is more" approach. This is ultimate a return to form of the way I used to train Thespis, with more of a focus on a small hand edited dataset." This is an interesting model.
Lewdiculous/DaturaCookie_7B-GGUF-IQ-Imatrix
Updated • 399 • 4Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. See examples and requirements in the model card page. Author: "Proficient at roleplaying and lighthearted conversation, this model is prone to NSFW outputs."
Lewdiculous/RP_Vision_7B-GGUF-IQ-Imatrix
Updated • 573 • 5Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. Author: "Beginning of a new line of RP capable vision models. RP Vision aims to be a smart RP model capable of providing a pretty, pliable and perfectly pleasant experience for the user. This model is vision capable using the mmproj file included in the mmproj folder. Vision is only compatible with KoboldCpp at this time."
Lewdiculous/Eris_PrimeV3-Vision-7B-GGUF-IQ-Imatrix
Updated • 1.06k • 13Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. Author: "Eris is back in Prime form with additional vision capabilities!"
Lewdiculous/Asherah_7B-GGUF-IQ-Imatrix
Updated • 388 • 7Note This is also a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples and requirements in the model card page. Author: "Asherah, goddess of all creation according to ancient myth was a huge inspiration for this model. The model started with a merge of four of Sanji Watsuki's models using various methods. This merge was then finetuned on Gnosis and Synthetic Soul, two datasets penned by myself."
Lewdiculous/Persephone_7B-GGUF-IQ-Imatrix
Updated • 201 • 4Note Author: "After being in a bit of a rut, I decided to take a radically different approach to produce something new and exciting. It seems to have worked out. I hope you enjoy! "If the first or second reply do not follow "quotes" asterisks format, reroll until it does. The longer you chat that way, the more the model will adhere to format."
Lewdiculous/Eris-Lelanacles-7b-GGUF-IQ-Imatrix
Updated • 216 • 4Note "Many experiments later Eris is back, in her latest form!" This is a general roleplay model.
Lewdiculous/Kool-Aid_7B-GGUF-IQ-Imatrix
Updated • 289 • 5Note "Come drink yours too!"
Lewdiculous/Sonya-7B-GGUF-IQ-Imatrix
Updated • 153 • 4Note Requester's description: "Despite being a general use model. It has strong RP potential and exhibit good memory overall while also having more technical knowledge compared to other 7B RP models."
Lewdiculous/Infinitely-Laydiculous-7b-longtext-GGUF-IQ-Imatrix
Updated • 170 • 7Note User request. Merge of: Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context Nitral-AI/Infinitely-Laydiculous-7B Experimental.
Lewdiculous/Eris_PrimeV3.05-Vision-7B-GGUF-IQ-Imatrix
Updated • 547 • 5Note This is a #Multimodal model with #Vision capabilities. Read the full card information if you also want to try that. See examples in the model card page. Author: "Model outputs are solid in quality, and relevant to given cards." This version was initially on the #experimental side, after many turns of conversation it can suffer from issues like: "A close bond... far from home... where Herp... and Derp... together... begin to..." I would recommend using the previous version.
Lewdiculous/RoleBeagle-11B-GGUF-IQ-Imatrix
Updated • 404 • 8Note User requested: "Scores unusually high for 10.7-11B". "A DPO-finetune from vicgalle/CarbonBeagle-11B-truthy over a subset of OpenHermesPreferences containting RP conversations. It keeps most of the intelligence from CarbonBeagle-11B, and hopefuly can role-play better." Benchmark numbers are pretty good.
Lewdiculous/Infinitely-Laydiculous-7B-GGUF-IQ-Imatrix
Updated • 141 • 7Note "Hopefully a shining model for roleplaying!"
Lewdiculous/Nina-v2-7B-GGUF-IQ-Imatrix
Updated • 214 • 4Note Author: "This model has been doing a good job staying in character. Sillytavern presets in presets folder."
Lewdiculous/Eris-Beach_Day-7b-GGUF-IQ-Imatrix
Updated • 213 • 4Note "Perhaps an experimental tropical mix of nice performing roleplay models." Experimental.
Lewdiculous/Infinitely-Laydiculous-9B-GGUF-IQ-Imatrix
Updated • 826 • 15Note Merge of: Endevor/InfinityRP-v1-7B l3utterfly/mistral-7b-v0.1-layla-v4 Lewdiculous coping: "I expect this to be smart enough and good for roleplaying while borrowing a bit of unalignment from the merged model." Instruct format and context size: - Extended Alpaca format (recommended). - The expected --contextsize this model can handle is 8192. The goal was a smarter model that's also good for roleplaying.
Lewdiculous/InfinityNexus_9B-GGUF-IQ-Imatrix
Updated • 247 • 4Note Merge of: Endevor/InfinityRP-v1-7B jeiku/NarrativeNexus_7B
Lewdiculous/kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF-IQ-Imatrix
Updated • 342 • 10Note Author: " I'm hoping that the result is more robust against errors or when merging due to "denseness", as the two models likely implement comparable reasoning at least somewhat differently."
Lewdiculous/kukulemon-7B-GGUF-IQ-Imatrix
Updated • 204 • 8Note Author: "A merger of two similar models with strong reasoning, hopefully resulting in "dense" encoding of said reasoning, was merged with a model targeting roleplay."
Lewdiculous/LemonadeRP-4.5.3-GGUF-IQ-Imatrix
Updated • 286 • 12Note Author: "7B roleplay focused model, creativity and less cliché is the focus of this merge."
Lewdiculous/Prima-LelantaclesV6.69-7b-GGUF-IQ-Imatrix
Updated • 289 • 4Note Author: "...not perfect, but damn is it good when it works." This is an experimental model.
Lewdiculous/Prima-LelantaclesV6.3-7b-GGUF-IQ-Imatrix
Updated • 206 • 3Note This is an experimental model.
Lewdiculous/Mika-Longtext-7b-GGUF-IQ-Imatrix
Updated • 329 • 4Note Author: "...should theoretically be better at long context." Maybe.
Lewdiculous/BuRP_7B-GGUF-IQ-Imatrix
Updated • 752 • 24Note Author: "So you want a model that can do it all? You've been dying to RP with a superintelligence who never refuses your advances while sticking to your strange and oddly specific dialogue format?" "Well, look no further because BuRP is the model you need."
Lewdiculous/Paradigm_Shift_7B-GGUF-IQ-Imatrix
Updated • 566 • 6Note Author: "A more compliant finetune of Paradigm. I have briefly tested this and it should more readily answer NSFW and difficult queries with fewer refusals. This model will be well suited to RP and question answering."
Lewdiculous/Paradigm_7B-GGUF-IQ-Imatrix
Updated • 133 • 4Note Author: "An incredibly effective and intelligent RP model designed to be the best bot you've ever used. I hope you like it!" "...less refusals." Merge of: - liminerity/Multiverse-Experiment-slerp-7b - jeiku/Alpaca_NSFW_Shuffled_Mistral - ResplendentAI/Datura_7B - ChaoticNeutrals/Eris_Remix_7B Experimental.
Lewdiculous/Sinerva_7B-GGUF-IQ-Imatrix
Updated • 581 • 1Note Author: "Decadent and rich in sensual prose, but beware, she is designed to humiliate and degrade her user when necessary."
Lewdiculous/InfinityRP-v1-7B-GGUF-IQ-Imatrix
Updated • 646 • 41Note Great model! Author: "This model was basically made to stop some upsetting hallucinations, so {{char}} mostly and occasionally will wait {{user}} response instead of responding itself or deciding for {{user}}, also, my primary idea was to create a cozy model that thinks." The supported --contextsize is 8192. Please read the full description for more information.
Lewdiculous/Eris-Daturamix-7b-v2-GGUF-IQ-Imatrix
Updated • 347 • 6Note Author: "Version 2!" Merge of: ResplendentAI/Datura_7B ChaoticNeutrals/Eris_Floramix_DPO_7B Experimental: For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used.
Lewdiculous/Eris-Daturamix-7b-GGUF-IQ-Imatrix
Updated • 80 • 4Note Merge of: ResplendentAI/Datura_7B Test157t/Eris-Floramix-7b Experimental: For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used.
Lewdiculous/Eris_Floramix_DPO_7B-GGUF-Imatrix
Updated • 193 • 4Note Author: "This is a mix between Eris Remix DPO and Flora DPO, a finetune of the original Eris Remix on the Synthetic_Soul_1k dataset." Experimental: For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used. The goal is to measure the (hopefully positive) impact of this data for consistent formatting in roleplay chatting scenarios.
Lewdiculous/Datura_7B-GGUF-Imatrix
Updated • 84 • 5Note Author: "Flora with a bit of toxicity." "I've been making progress with my collection of tools, so I thought maybe I'd try something a little more toxic for this space. This should make for a more receptive model with fewer refusals." Experimental: For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used. The goal is to measure the (hopefully positive) impact of this data for consistent formatting in roleplay chatting scenarios.
Lewdiculous/Layris_9B-GGUF-IQ-Imatrix
Text Generation • Updated • 546 • 16Note Merge of: ChaoticNeutrals/Eris_Remix_7B l3utterfly/mistral-7b-v0.1-layla-v4 ...a top performer and a very free model together!
Lewdiculous/FuseChat-Kunoichi-10.7B-GGUF-IQ-Imatrix
Updated • 242 • 8Note Merge of: FuseAI/FuseChat-7B-VaRM SanjiWatsuki/Kunoichi-DPO-v2-7B
Lewdiculous/Eris_Remix_7B-GGUF-IQ-Imatrix
Text Generation • Updated • 206 • 11Note "Eris is back... With a vengeance!" "...and a special sauce."
Lewdiculous/Copium-Cola-9B-GGUF-IQ-Imatrix
Text Generation • Updated • 402 • 7Note "Dare we cope?"
Lewdiculous/Bepis_9B-GGUF-IQ-Imatrix
Text Generation • Updated • 352 • 5Note A new 9B model from jeiku. This one is smart, proficient at markdown, knows when to stop talking, and is quite soulful. The merge was an equal 3 way split between: https://huggingface.co/ChaoticNeutrals/Prodigy_7B, https://huggingface.co/Test157t/Prima-LelantaclesV6-7b, and https://huggingface.co/cgato/Thespis-CurtainCall-7b-v0.2.1
Lewdiculous/mistral-7b-v0.1-layla-v4-GGUF-IQ-Imatrix
Text Generation • Updated • 412 • 7Note Ideal for NSFW scenarios. "Removed all refusals, removed any mention of AI Assistant". Mistral 7B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation.
Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix
Text Generation • Updated • 374 • 9Note "This is an attempt to create a model that combines multiple "established" 7Bs and a very small WIP private dataset with Eros' raw creative power. In terms of instruction formats, ChatML and Alpaca work best."
Lewdiculous/Eris_7B-GGUF-IQ-Imatrix
Text Generation • Updated • 242 • 5Note Merge of: ChaoticNeutrals/Prodigy_7B Test157t/Prima-LelantaclesV6-7b Fusion of beasts!
Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix
Text Generation • Updated • 263 • 5Note Merge of: Test157t/West-Pasta-Lake-7b Test157t/Lelantacles6-Experiment26-7B This is an experimental model. Slight improvements over the previous version.
Lewdiculous/opus-v1.2-7b-GGUF-IQ-Imatrix
Text Generation • Updated • 630 • 6Note Opus V1 (7B): 32K context. Story-writing & role-playing model. "Uncensored model for steerable story-writing and role-playing". "Prompting guide: https://dreamgen.com/docs/models/opus/v1".
Lewdiculous/Prima-LelantaclesV5-7b-GGUF
Text Generation • Updated • 90 • 4Note Merge of: Test157t/Pasta-Lake-7b Test157t/Prima-LelantaclesV4-7b-16k
Lewdiculous/EndlessRP-v3-7B-GGUF-Imatrix
Text Generation • Updated • 136 • 11Note The sauce: mistralai/Mistral-7B-v0.1 Elizezen/Hameln-japanese-mistral-7B fblgit/una-cybertron-7b-v3-OMA+.\toxic-dpo-v0.1-NoWarning-lora cgato/Thespis-CurtainCall-7b-v0.1.2+Doctor-Shotgun/mistral-v0.1-7b-pippa-metharme-lora "This model is recommended for RP, but you can use it as assistant as well."
Lewdiculous/Loyal-Toppy-Bruins-Maid-7B-DARE-GGUF-Imatrix
Text Generation • Updated • 250 • 13Note The sauce: mistralai/Mistral-7B-v0.1 rwitz/go-bruins-v2 chargoddard/loyal-piano-m7 Undi95/Toppy-M-7B NeverSleep/Noromaid-7b-v0.1.1 A surprisingly good small model for RP! Use alpaca format, --contextsize 8192.
Lewdiculous/Prodigy_7B-GGUF-Imatrix
Text Generation • Updated • 191 • 6Note Merge of: macadeliccc/WestLake-7B-v2-laser-truthy-dpo ChaoticNeutrals/This_is_fine_7B This is an experimental model.
Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix
Text Generation • Updated • 1.16k • 28Note Merge of: SanjiWatsuki/Kunoichi-DPO-v2-7B Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context This has been my personal favourite and daily-driver role-play model for a while, so I decided to make new quantizations for it using the full F16-Imatrix data.
Lewdiculous/Kunoichi-DPO-v2-7B-GGUF-Imatrix
Text Generation • Updated • 2.85k • 35Note My general all around recommended small model for most people looking for a good roleplay chatting experience in a small model size that's also pretty smart.
Lewdiculous/Prima-LelantaclesV4-7b-16k-GGUF
Text Generation • Updated • 103 • 6Note Merge of: Test157t/Yarncules-7b-128k Test157t/Prima-LelantaclesV3-7b
Lewdiculous/Pasta-Lake-7b-GGUF
Text Generation • Updated • 103 • 5Note Merge of: Test157t/Pasta-PrimaMaid-7b macadeliccc/WestLake-7B-v2-laser-truthy-dpo