Community
ISTA-DASLab releases GSQ-RCO quantized GGUF of DeepSeek-V4.1-Flash-1017
The quants are published on Hugging Face, but Llama.cpp does not yet support the architecture, so the model runs only on forks such as Xolotl or Maya, according to the poster.
Every outlet that ran it 1 article
r/LocalLLaMACommunityLead