QuantTrio/DeepSeek-V3.2-AWQ is a quantized (AWQ) version of DeepSeek's V3.2 large language model. It includes a custom chat template and tokenizer optimized for efficient inference. The model is suitable for local deployment where full-precision weights would be too large.
In the Foundation models & chat space, DeepSeek takes a focused approach. It focuses on running the DeepSeek V3.2 model efficiently on consumer or enterprise hardware using AWQ quantization. DeepSeek is an open-source project aimed at developers and researchers. The project is open source (MIT). DeepSeek is available on the web, the command line, and API.
Behind DeepSeek is QuantTrio, and the product first shipped in 2024. The project is developed in the open on GitHub with 5k stars. Among its 3 catalogued features are Large Language Model, Quantized Inference, and Chat Completion.
Latest indexed changes and source events
QuantTrio/DeepSeek-V3.2-AWQ verified by the PulseGate indexer
Other apps tracked under the same category.
