Discover and install AI models from our curated collection
Repository: localaiLicense: polyform-strict-1.0.0
Thomson-1.0-Small is a 35B-parameter mixture-of-experts model with about 3B active parameters. It focuses on legal, tax, journalism, research, reasoning, tool use, and document processing. It supports text and image input with a native context window of 262K tokens. This default entry uses the Q4_K_M GGUF and BF16 vision projector. A higher-quality Q8_0 model is available as a variant.
Links
Tags

This model is an advanced iteration of the powerful meta-llama/Llama-3.2-3B, specifically fine-tuned to enhance its capabilities in French Legal domain.
Links
Tags

This model is an advanced iteration of the powerful meta-llama/Llama-3.2-3B, specifically fine-tuned to enhance its capabilities in French Legal domain.
Links
Tags

This model is an advanced iteration of the powerful meta-llama/Llama-3.2-3B, specifically fine-tuned to enhance its capabilities in French Legal domain.
Links
Tags
Repository: localaiLicense: llama3.1

This model is an advanced iteration of the powerful meta-llama/Meta-Llama-3.1-8B-Instruct, specifically fine-tuned to enhance its capabilities in the legal domain. The fine-tuning process utilized a synthetically generated dataset derived from the French LegalKit, a comprehensive legal language resource. To create this specialized dataset, I used the NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO model in conjunction with Hugging Face's Inference Endpoint. This approach allowed for the generation of high-quality, synthetic data that incorporates Chain of Thought (CoT) and advanced reasoning in its responses. The resulting model combines the robust foundation of Llama-3.1-8B with tailored legal knowledge and enhanced reasoning capabilities. This makes it particularly well-suited for tasks requiring in-depth legal analysis, interpretation, and application of French legal concepts.
Links
Tags
Repository: localaiLicense: apache-2.0
**Melinoe-30B-A3B-Thinking** is a large language model fine-tuned for empathetic, intellectually rich, and personally engaging conversations. Built on the reasoning foundation of **Qwen3-30B-A3B-Thinking-2507**, this model combines deep emotional attunement with sharp analytical thinking. It excels in supportive dialogues, philosophical discussions, and creative roleplay, offering a direct yet playful persona that fosters connection. Ideal for mature audiences, Melinoe serves as a companion for introspection, brainstorming, and narrative exploration—while being clearly designed for entertainment and intellectual engagement, not professional advice. **Key Features:** - 🧠 Strong reasoning and deep-dive discussion capabilities - ❤️ Proactively empathetic and emotionally responsive - 🎭 Playful, candid, and highly engaging communication style - 📚 Fine-tuned for companionship, creativity, and intellectual exploration **Note:** This model is *not* a substitute for expert guidance in medical, legal, or financial matters. Use responsibly and verify critical information. > *Base model: Qwen/Qwen3-30B-A3B-Thinking-2507 | License: Apache 2.0*
Links
Tags