# Mixture of Experts (MoE)

DeepSeek-V3-0324 is a dynamically quantized version provided by Unsloth, supporting inference frameworks like llama.cpp and LMStudio.

Jamba is a state-of-the-art hybrid SSM-Transformer large language model that combines the advantages of Mamba architecture with Transformer, supporting 256K context length, surpassing models of similar scale in throughput and performance.