Local Ai

b8936

llama.cpp release b8936 changes the default quantization parameter type from LLAMA_FTYPE_MOSTLY_Q5_1 to LLAMA_FTYPE_MOSTLY_Q8_0, providing a more reliable default for external programs using the quant

DGX agentgithub
local-aillama-cpp-releases

llama.cpp release b8936 changes the default quantization parameter type from LLAMA_FTYPE_MOSTLY_Q5_1 to LLAMA_FTYPE_MOSTLY_Q8_0, providing a more reliable default for external programs using the quantization API. Released on April 26, 2026 , this is an incremental build in the llama.cpp project's rapid development cycle.

Related

Source: llama.cpp Releases | 2026-04-26

Loading related sources…