# 128k Long Context

An efficient language model specifically designed for software engineering projects, featuring a lightweight design and supporting a 128k large context window, suitable for complex coding tasks.

Devstral is an intelligent LLM specifically designed for software engineering tasks, jointly developed by Mistral AI and All Hands AI. It excels in code exploration, multi-file editing, and driving software engineering agents.

Devstral is a large language model for software engineering task agents, developed in collaboration between Mistral AI and All Hands AI. It excels at using tools to explore codebases, edit multiple files, and drive software engineering agents.

Devstral is an intelligent large language model developed by Mistral AI in collaboration with All Hands AI for software engineering tasks, excelling in codebase exploration, multi-file editing, and driving software engineering agents.

Zero-Mistral-24B is an improved text-only model based on Mistral-Small-3.1-24B-Instruct-2503, primarily adapted for Russian and English, with the original visual capabilities removed to focus on text generation tasks.

A multimodal large model launched by Mistral-Community, supporting image and text processing with 128k context length and variable image size handling capabilities.

Based on the QwQ-32B reasoning and thinking model, it incorporates features from multiple top-tier reasoning models, focusing on reducing 'overthinking' in prompts, suitable for creative use cases and in-depth reasoning.

A Mixture of Experts (MoE) model with adjustable reasoning capabilities, enhancing inference and text generation through collaboration of four 8B models

Llama-SEA-LION-v3.5-70B-R is a hybrid-function large language model optimized for Southeast Asian languages, supporting 13 languages with capabilities in complex reasoning and general text generation.

Llama-SEA-LION-v3.5-8B-R is an 8B-parameter large language model optimized for Southeast Asian languages, supporting 13 languages with capabilities in complex reasoning and general text generation.

Cogito v1 Preview is an instruction-tuned generative model based on Qwen2.5-32B, supporting over 30 languages with a context length of 128k, optimized for programming, STEM, instruction following, and general assistance.

The xLAM-2 series are Large Action Models (LAMs) built with advanced data synthesis and training pipelines, specializing in multi-turn conversations and tool usage, demonstrating exceptional performance in function calling and agent tasks.

This is a Qwen2.5 MOE (Mixture of Experts) model, composed of two Qwen 2.5 DeepSeek (censored/regular and uncensored) 1.5B models, forming a 4B model where the uncensored version of DeepSeek Qwen 2.5 1.5B dominates the model's behavior.

Llama 3.2-Vision is a multimodal large language model developed by Meta, supporting image and text inputs, optimized for visual recognition, image reasoning, and description tasks.

Llama 3.1 is a multilingual large language model collection developed by Meta, including 8B, 70B, and 405B parameter versions, supporting 8 languages, optimized for dialogue use cases.

A 7B-parameter uncensored creative writing model based on Llama 3.2 architecture, supporting 128k context length, optimized for novel writing, plot generation, and roleplaying

Llama 3.2 is a 1B and 3B parameter-scale multilingual pre-trained and instruction-tuned generative model from Meta, optimized for multilingual dialogue use cases and supporting 8 official languages.

Llama 3.2 is a collection of multilingual large language models released by Meta, including pre-trained and instruction-tuned versions with 1B and 3B parameter scales, optimized for multilingual conversational use cases and supporting 8 official languages.

Llama 3.2 is a set of pre-trained and instruction-tuned generative models, including 1B and 3B scales, optimized for multilingual dialogue use cases, including agent retrieval and summarization tasks.

Vikhr-Nemo is a bilingual large language model optimized based on Mistral-Nemo-Instruct-2407, specifically designed for Russian and English, supporting various tasks such as logical reasoning, text summarization, and code generation.

Llama 3.2-Vision is a multimodal large language model developed by Meta, supporting image and text input with text output, excelling in visual recognition, image reasoning, image captioning, and visual question answering tasks.

Llama 3.2-Vision is a series of multimodal large language models developed by Meta, available in 11B and 90B scales, supporting image + text input and text output, optimized for visual recognition, image reasoning, image captioning, and visual question answering tasks.

Llama 3.2 is a multilingual large language model series developed by Meta, including 1B and 3B scale pre-trained and instruction-tuned generative models, optimized for multilingual dialogue scenarios, supporting text input/output.

Llama 3.2 is a multilingual large language model series developed by Meta, including 1B and 3B scale pre-trained and instruction-tuned generative models, optimized for multilingual dialogue scenarios, supporting intelligent retrieval and summarization tasks.

Llama 3.2 is a multilingual large language model series launched by Meta, including 1B and 3B parameter pre-trained and instruction-tuned generative models, optimized for multilingual dialogue scenarios, supporting agent retrieval and summarization tasks.

Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.

GGUF quantized version of Meta Llama 3.1 8B instruction-tuned model, suitable for multilingual dialogue scenarios

Meta Llama 3.1 is a series of multilingual large language models, including 8B, 70B, and 405B pre-trained and instruction-tuned generative models, optimized for multilingual dialogue scenarios.