Granite 4.0 H-Small (FP8) is a small FP8 quantized version of the Granite series of language models developed by IBM, designed to provide professional, accurate, and secure responses. The model uses the FP8 precision format, optimizing inference efficiency while maintaining performance.

Natural Language ProcessingTransformers

trlm-135m is a small research prototype language model with 135 million parameters. It is built on SmolLM2-135M-Instruct and has undergone a three-stage fine-tuning process to explore how small language models can acquire step-by-step reasoning abilities.

Natural Language ProcessingTransformersEnglish

QuestA is an innovative framework that enhances the reasoning ability of large language models through a question-enhanced approach. It integrates partial solutions during the reinforcement learning training process, significantly improving the model's performance on complex tasks such as mathematical reasoning, especially achieving optimal results on small-parameter models.

Natural Language ProcessingTransformers

MobileLLM-R1 is a series of efficient inference language models released by Meta, focusing on solving mathematical, programming, and scientific problems. This model can still achieve excellent performance with a relatively small parameter scale, and provides a complete training recipe and data sources to support reproducible research.

Natural Language ProcessingTransformersEnglish

This is a distilled small language model based on the GPT architecture. It is distilled from a 20B parameter model to a 1.7B parameter model and converted to the GGUF format for use in llama.cpp. The model has efficient inference performance and low resource requirements.

Natural Language ProcessingGguf

Gemma 3 is a lightweight open-source multimodal model family launched by Google, built on the same research technology as Gemini. The 270M version is the smallest instruction-tuned model among them, supporting over 140 languages and having a 32K context length, suitable for text generation tasks in resource-constrained environments.

MultimodalTransformers

Tiny GptOssForCausalLM is a minimized causal language model designed specifically for unit tests of the TRL (Transformer Reinforcement Learning) library. This model is extremely small in scale and is mainly used to verify the correctness of the operation of reinforcement learning-related functions in the TRL library under a specific model architecture.

Natural Language ProcessingTransformers

Cthulhu is a large model fusion project based on Mistral Small v3.2 and v3.1. It is a super powerful 24B parameter language model created by fusing multiple cutting-edge fine-tuned models. It has octopus-like multifaceted features, providing uncensored creative text generation capabilities, and excels in prose writing, instruction following, and esoteric knowledge expression.

Natural Language ProcessingTransformersEnglish

Cthulhu 24B 1.1 GGUF is a large language model fused based on the Mistral Small series of models, integrating 17 different model components. It has the capabilities of creative writing, uncensored dialogue, and rich language interaction. Inspired by the Cthulhu mythos, this model aims to provide a'super fusion' experience that goes beyond the capabilities of a single model.

Natural Language ProcessingTransformersEnglish

Magistral Small 1.1 is a high - efficiency reasoning model with 24 billion parameters, built on the basis of Magistral Small 3.1. It has new reasoning capabilities, supports multiple languages, and uses the Apache 2.0 license. It can be locally deployed and run on a single RTX 4090 or a MacBook with 32GB of memory.

Natural Language ProcessingGgufMultiple Languages

A small multilingual vision-language model based on the Mistral architecture, optimized for image-to-text conversion tasks, supporting over 20 languages, and performance-optimized for Apple chips through MLX quantization.

MultimodalSafetensorsMultiple Languages

Devstral Small 1.1 GGUF is a large language model specifically designed for software engineering tasks. It combines the technical advantages of Mistral AI and All Hands AI and performs excellently in code processing and software engineering agency.

Natural Language ProcessingGgufEnglish

Devstral Small 1.1 is a large language model optimized for software engineering tasks, developed in collaboration by Mistral AI and All Hands AI, supporting multiple languages and tool invocation.

Natural Language ProcessingSafetensorsMultiple Languages

Devstral-Small-2507 is a small text generation model developed by mistralai. It supports multiple languages and is optimized for Apple chips.

Natural Language ProcessingSafetensorsMultiple Languages

SmolLM3 is a language model with 3 billion parameters, aiming to break the performance boundary of small models. It supports 6 languages, has advanced reasoning ability and long context processing ability, and is a fully open-source model.

Natural Language ProcessingTransformersMultiple Languages

Impish_LLAMA_4B is a large language model with 4 billion parameters built on the NVIDIA pruned model, specifically optimized for role-playing and adventure scenarios. While maintaining a relatively small parameter scale, this model demonstrates excellent response capabilities and context awareness, capable of generating coherent adventure stories and providing certain assistant functions.

Natural Language ProcessingTransformersEnglish

Mistral Small 3.2 24B Instruct 2506 is a multilingual large language model that supports text and image input and text output, with a context length of 128k.

MultimodalGgufMultiple Languages

Jan Nano is a small language model fine - tuned based on the Qwen3 architecture, designed for local and embedded environments, combining efficiency and long - context processing capabilities.

Natural Language ProcessingGguf

LORA is a fine-tuned version of the Mistral Small 24B Instruct model, optimized for child-friendly language generation in educational scenarios. It focuses on providing safe, age-appropriate, and engaging storytelling services for children aged 6 to 12.

Natural Language ProcessingTransformersGerman

Devstral-Small-2505 is a small language model based on the Mistral architecture, supporting text generation tasks and capable of basic visual functions through compatible mmproj files.

MultimodalGguf