# Low Memory Optimization

This is a quantized version of Gryphe's Codex-24B-Small-3.2 model, which optimizes the running efficiency under different hardware conditions through quantization technology.

This is a Jedi - 7B - 1080p model quantized using llama.cpp, offering multiple quantization types for users to choose from, balancing file size and model quality.

Legion-V2.1-LLaMa-70B-Elarablated-v0.8-hf is a quantized version based on LLaMa-70B, optimized using llama.cpp, offering multiple quantization options to accommodate different hardware requirements.

A quantized version of the NVIDIA Llama-3.1-Nemotron-Nano-4B-v1.1 model, processed with llama.cpp tools for various quantization methods, suitable for running in resource-constrained environments.

Qwen2.5-Omni is an end-to-end multimodal model capable of perceiving various modalities such as text, images, audio, and video, and generating text and natural speech responses in a streaming manner.

A quantized version based on Qwen/Qwen3-1.7B, using llama.cpp for quantization, supporting multiple quantization types, suitable for text generation tasks.

The Llamacpp imatrix quantization version of Qwen3-4B provided by the Qwen team, supporting multiple quantization types and suitable for text generation tasks.

Llama-3.2-1B-Instruct is a 1B-parameter instruction-fine-tuned model based on the Llama architecture, offering multiple quantization formats to accommodate different hardware requirements.

The GGUF quantized version of Qwen2.5-72B-Instruct, supporting multiple precision formats for efficient inference across different hardware environments.

mxbai-rerank-large-v2 is a multilingual text reranking model that supports multiple languages and various quantization formats, suitable for different hardware environments.

Meta-Llama-3-8B is an 8B-parameter large language model based on the GGUF format, supporting multiple quantized versions for various hardware environments.

RWKV-7 architecture with 2.9 billion parameters, supporting multilingual text generation tasks

This is a GGUF quantized version based on Wan-AI/Wan2.1-T2V-1.3B, specifically designed for text-to-video generation tasks, compatible with comfyui-gguf and gguf nodes.

The GGUF quantized version of Mochi is a text-to-video generation model that includes a GGUF encoder and GGUF variational autoencoder, suitable for fast video content generation.

Mochi is a text-to-video generation model based on the GGUF quantized version, supporting video content generation from text descriptions.

Mixtral-8x7B is a pre-trained generative sparse mixture of experts model that outperforms Llama 2 70B on most benchmarks.

StarCoder2-3B is a 3-billion-parameter code generation model trained on 17 programming languages, supporting a context window of 16,384 tokens.

This is a sharded version of the BLIP-2 model implemented with Flan T5-xl for image-to-text tasks such as image captioning and visual question answering. Sharding allows it to be loaded in low-memory environments.

Long-sequence Nyströmformer model trained on WikiText-103 v1 dataset, supports sequence processing up to 4096 tokens

Nystromformer model trained on the WikiText-103 dataset, supporting long sequence processing (2048 tokens)