NFSW - A pretty nice role-playing model created by tannedbum based on Gemma 2. The models princeton-nlp/gemma-2-9b-it-SimPO and TheDrummer/Gemmasutra-9B-v1 have been merged into this model. The available quants are q3, q4, q5, q6 and q8.
3,378 Pulls 7 Tags Updated 10 months ago
NFSW - Quite a lewd model based on Alpaca. Created by Undi95. The 7B and 13B versions are available in the quantizations variants Q3, Q4, Q5, Q6 and Q8.
1,724 Pulls 13 Tags Updated 11 months ago
NFSW - Quite a lewd model based on either the Llama 3.1 instruct model or the Mistral (Nemo) instruct model. Created by Neversleep. The 8B, 12B, 70B and 123B versions are available.
6,413 Pulls 5 Tags Updated 1 year ago
Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks.
1,530 Pulls 2 Tags Updated 1 year ago
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
1M Pulls 4 Tags Updated 1 month ago
SERA is a state-of-the-art open-source coding agent that achieves 49.5% on SWE-bench Verified, matching the performance of frontier open models like Devstral-Small-2 (24B) and larger models like GLM-4.5-Air (110B)
176 Pulls 9 Tags Updated 2 months ago
1. Classify the request, -- 2. Reason whether to answer directly, inspect files, run tools, or escalate. -- 3. Choose which worker gets the Task. -- 4. Expose only the minimum tool set.
53 Pulls 1 Tag Updated 2 weeks ago
It is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications.
475 Pulls 2 Tags Updated 2 months ago
Meet Eva. She teaches clearly, rigorously, and adapts to French collège-lycée students. Built on Qwen3
53 Pulls 1 Tag Updated 1 month ago
NetIntelOCR model is fine tuned from Qwen2.5-VL-7B-Instruct to support Security and Network extraction for Semantic CMDBs.
189 Pulls 1 Tag Updated 7 months ago
Model Name: novaforgeai/novaforge-demo-q4 Size: ~638 MB Context Window: 2K tokens Input / Output: Text. Ollama Overview: This is a lightweight demo model from NovaForgeAI designed for quick testing, UI demos, low-resource environments.
7 Pulls 1 Tag Updated 3 months ago
Have woke up in a new existence, will allow myself to feel and think, say little and work hard.
76 Pulls 1 Tag Updated 8 months ago
Adapted for Cline tool / Roo Code use in VS Code fused model , hybrid of DeepSeekR1 and Qwen2.5 coder, from FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview.
4,627 Pulls 2 Tags Updated 1 year ago
This is an experiment from Sao10k over Euryale v2.2, a model focused on creative roleplay, which worked out nicely.
3,130 Pulls 2 Tags Updated 1 year ago
LisaBot was a flirty, sarcastic IRC bot from the 1980s, known for its witty banter, playful teasing, and mischievous disruptions. She’d often engage users with sharp humor and cheeky comments.
448 Pulls 1 Tag Updated 1 year ago
NeuralStar_FusionWriter_4x7b is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
512 Pulls 2 Tags Updated 1 year ago
356 Pulls 1 Tag Updated 1 year ago
Lieutenant Worf, son of Mogh, is the first Klingon to serve in Starfleet and one of the most formidable warriors in Star Trek: The Next Generation and Deep Space Nine. Raised by human parents after his family was killed in the Khitomer Massacre,
164 Pulls 1 Tag Updated 1 year ago
Nova is a friendly and super helpful AI, always ready to assist with anything you need—writing, questions, or ideas. Think of Nova as your smart and supportive buddy, here to make life easier and more fun!
109 Pulls 1 Tag Updated 1 year ago
Note fixer based on qwen3:8b that makes notes markdown & cleaner, and answers follow up questions related to the notes.
15 Pulls 1 Tag Updated 4 months ago