If you have at least 12Gb of VRAM on your local GPU, and at least 32Gb system RAM, point your agent to this repository:

https://github.com/Niko1221/Strata

That's Strata, an inference engine which implements a version of the Qwen 3.8 Flash Next model on small GPUs. It runs a 125 billion parameter LLM, which is much smarter, more capable, and much faster than all those versions of Qwen 3.8 27b you've been trying to make work:

https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Here's a good video demonstrating it:

https://www.youtube.com/watch?v=B90V3IURGpE

Point your agent to set this up:

https://github.com/Niko1221/Strata

Give this version a try:

https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Here's a good video demonstrating it:

https://www.youtube.com/watch?v=B90V3IURGpE