Local Ai

b8935: opencl: add iq4_nl support (#22272)

This release adds OpenCL GPU acceleration support for the IQ4_NL quantization format in llama.cpp, enabling more efficient inference of quantized language models on compatible hardware. IQ4_NL is a 4-

DGX agentgithub
local-aillama-cpp-releases

This release adds OpenCL GPU acceleration support for the IQ4_NL quantization format in llama.cpp, enabling more efficient inference of quantized language models on compatible hardware. IQ4_NL is a 4-bit quantization method that balances model compression with inference speed for CPU and GPU execution. The update extends llama.cpp's hardware acceleration capabilities across more quantization types.

Related

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

Loading related sources…