# Large model optimization

Quantized version of ICONN-1, offering multiple quantization options to meet different performance and quality requirements

This is a quantized version of google/gemma-3-27b-it, supporting visual-text input and text output. Optimized through weight quantization and activation quantization, it enables efficient inference with vLLM.

Valkyrie-49B-v1 is a 49B-parameter large language model based on llama.cpp, offering multiple quantization versions suitable for different hardware configurations.

A large language model fine-tuned based on Mistral-Small-3.1-24B-Base-2503-hf-DanChat, specializing in personalized text generation

The Llama 4 series is a native multimodal AI model launched by Meta. It adopts the Mixture of Experts architecture, supports text and image interaction, and performs excellently in various language and visual tasks.

CogVideoX is an open-source version of the video generation model from Qingying. The 5B version has a larger model scale and can generate higher-quality video content.

FP8 quantized version of Meta-Llama-3.1-405B-Instruct, suitable for multilingual commercial and research purposes, specially optimized for assistant robot scenarios.

This is a ctranslate2 converted version of the antony66/whisper-large-v3-russian model, optimized for Russian speech recognition tasks.

An automatic speech recognition model fine-tuned on Polish datasets based on Whisper Large v2, supporting Polish speech-to-text tasks.

This is a speech recognition model fine-tuned on a specific dataset based on jonatasgrosman/wav2vec2-large-xlsr-53-spanish model, supporting Spanish.

This is an automatic speech recognition model based on the wav2vec2 XLS-R architecture, specifically optimized for Norwegian Bokmål and trained on the NPSC dataset.

This is a large automatic speech recognition (ASR) model based on the wav2vec2 architecture, specifically trained for Norwegian written language (Bokmål).

This model is a fine-tuned version based on jonatasgrosman/wav2vec2-large-xlsr-53-spanish for Spanish speech recognition tasks.