This is a Q8_0 quantized GGUF version of the Vikhr-Nemo-12B-Instruct model, optimized for Russian language tasks. It supports conversational use and instruction following. The model is provided by VlSav and is compatible with llama.cpp and other GGUF-compatible runtimes for efficient local inference.
In the Foundation models & chat space, Vikhr Nemo 12B Instruct R 21 09 24 Q8 0 takes a focused approach. It focuses on running a capable Russian-language LLM locally with efficient quantization for consumer hardware. Vikhr Nemo 12B Instruct R 21 09 24 Q8 0 is an open-source project aimed at russian-speaking developers and users. The project is open source (MIT). Vikhr Nemo 12B Instruct R 21 09 24 Q8 0 is available on the web and the command line.
VlSav builds and maintains Vikhr Nemo 12B Instruct R 21 09 24 Q8 0, and the product first shipped in 2023. The project is developed in the open on GitHub with 121k stars and 1.2k commits in the last 90 days. Among its 4 catalogued features are Russian Language Model, Instruction Following, and GGUF Quantization.
Latest indexed changes and source events
VlSav/Vikhr-Nemo-12B-Instruct-R-21-09-24-Q8_0-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
