AI & Compute
Local LLMs, CUDA, inference, image and video generation, TTS.
Guides 6
- Run MiniMax H3 Locally with Diffusers
MiniMax H3 generates video and audio together and needs two ~62 GB BF16 components. Run it on one high-memory GPU or split it across two 48 GB cards — Modular Diffusers, no ComfyUI.
- Install ROCm 7.14 on AMD Strix Halo / Ryzen AI Max+
Install and verify ROCm 7.14 with gfx1151 support on a Strix Halo (Ryzen AI Max+) laptop — repository, the amdrocm-core-dev package set, permissions, and rocminfo/HIP/llama.cpp verification.
- Run llama.cpp on AMD Strix Halo: ROCm and Vulkan Setup
Practical llama.cpp setup for Strix Halo (Ryzen AI Max+ / Radeon 8060S) — both backends (ROCm/HIP and Vulkan), which to pick, build commands, device selection, memory and large-context notes.
- Recommended llama.cpp Setup for Strix Halo
The starting point we recommend on AMD Strix Halo (Ryzen AI Max+ / Radeon 8060S) for llama.cpp: ROCm as the default backend, Vulkan as the fallback, and when MTP speculative decoding is worth enabling.
- Set Up Vulkan Compute on AMD Strix Halo / Radeon 8060S
Get Vulkan compute working on Strix Halo with the Mesa RADV driver — Kisak PPA setup, exact packages, vulkaninfo verification, and a llama.cpp Vulkan build.
- Build llama.cpp with CUDA for NVIDIA Blackwell
Compile llama.cpp for Blackwell GPUs (sm_120) with a current CUDA toolkit — correct architecture flags, build commands, and fixes for the errors you will actually hit.
Tools 2
- Video Resolution Calculator
Find video and image generation sizes divisible by your model's required multiple (8, 16, 32 or 64) for a target aspect ratio — or check whether a resolution you already have divides cleanly.
- GPU Model Fit Calculator
Calculate whether an LLM fits in GPU memory. Uses exact GGUF artifact sizes for preset models, parameter-count estimates with provenance labels otherwise, and includes measured GTT usage from the How Quant test machine.
Benchmarks 1
Reference 3
- llama.cpp Common Options
The llama.cpp flags you will actually use — GPU offloading, context and KV cache, performance, and sampling — grouped and one line each.
- AMD Strix Halo Local AI Compatibility
Which local-AI runtimes work on Strix Halo (Ryzen AI Max+ / Radeon 8060S) — llama.cpp on ROCm and Vulkan tested at pinned versions, PyTorch tracked but untested, with backend and status per combination.
- Understanding RAM, GTT, and GPU Memory on AMD Strix Halo
Why tools report different memory sizes on Strix Halo — unified memory architecture, GTT aperture vs usable RAM, what the kernel, ROCm, Vulkan and llama.cpp each report, with measured numbers.