A Hugging Face contributor and Arch Linux package maintainer built a bootable Arch Linux ARM setup for the ASUS ProArt P16 H7607BA-SE033W, a laptop with 128GB of RAM, 6,144 CUDA cores and a 2TB SSD that ships with official Windows-only support. The build incorporates NVIDIA's Ubuntu kernel work, custom ACPI overrides, a patched hid-asus driver for the keyboard, and official NVIDIA and ASUS firmware, with 7-Zip performance matching Windows and the OS correctly reporting the full 116GiB unified memory pool to CUDA.
josie.lol
· 2026-10-19
A new project called PS5LM runs llama.cpp on a jailbroken PS5's GPU, loading GGUF language models and serving them to other devices on the same network, such as laptops and phones. It exposes OpenAI-style and Anthropic-style endpoints, works with tools like Claude Code, and can also run decision models that answer TypeSafe's /v1/systemone API, the same interface used by the PC tool Ollaya. The console uses its Vulkan backend on its RDNA 2 GPU, with 11.4 GB of shared memory available for models and context, and needs no PC, cloud connection or account to operate.
github.com
· 2026-10-16
A developer has published Janus, an open-source single Go binary that runs local .gguf language models on AMD, Intel or Nvidia GPUs via Vulkan, or on CPU, without requiring Python, Docker or Ollama. It exposes an OpenAI-compatible API alongside a built-in web UI with chat, tool-calling, memory and file-handling features, and supports hot-swapping models without restarting.
github.com
· 2026-10-01
Following a rushed 'Lite' GGUF release four days after Qwen 3.8 27B launched, the team has now finished fully optimized ShapeLearn quantizations and benchmarked them against both the Lite versions and rival quants. The full models push the quality-versus-speed tradeoff further, with all five new variants topping the performance frontier across six GPU test configurations.
byteshape.com
· 2026-09-18
A benchmarking study tested several GGUF quantizations of the Qwen3.8 27B model against benchmarks including GPQA Diamond, IFBench, and Terminal-Bench 2.1. The 17GB Q4_K_M version performed on par with the full 55GB BF16 model on coding tasks and fits on a consumer 24GB GPU, while the smallest 6.2GB 1-bit version dropped to near-random accuracy on reasoning tasks, with longer reasoning chains making results worse.
quesma.com
· 2026-09-08
GoKawiil