AI Model2026
Provides non-uniform GGUF quantizations of DeepSeek-V4.1-Flash-1017, using GSQ and RCO to allocate precision per tensor under a size budget. The IQ2_XXS build matches the base model on the three reported benchmarks.
Provides non-uniform GGUF quantizations of DeepSeek-V4.1-Flash-1017, using GSQ and RCO to allocate precision per tensor under a size budget. The IQ2_XXS build matches the base model on the three reported benchmarks.