#AMD

How Far Has AMD ROCm Come in Catching Up to CUDA?

Based on EE Times' interview with AMD AI Software VP Anush Elangovan, we assess the ROCm vs CUDA ecosystem gap. Includes hands-on experience with ROCm breaking four times on Strix Halo, plus practical guidance on choosing between NVIDIA, AMD, and Apple Silicon.

LLM-jp-4-32B-A3B on ROCm + Strix Halo: 41% Faster Than Qwen3.5

Benchmarking NII's LLM-jp-4-32B-A3B-thinking on EVO-X2 (Ryzen AI Max+ 395) with ROCm. 62.9 t/s vs Qwen3.5-35B-A3B's 44.7 t/s. Covers thinking control issues, KV cache trade-offs, knowledge cutoff, Japanese quality comparisons, code generation tests, and training data composition.

Running Lemonade on Strix Halo (EVO-X2): Vulkan Shared Memory Leaks and ROCm Stability

Real-world testing of AMD Lemonade v10.0.1 on Ryzen AI Max+ 395. LLM, image generation, speech recognition, and TTS running simultaneously, NPU Hybrid execution, Vulkan vs ROCm benchmarks, and discovering shared memory leaks.

AMD's Lemonade Local AI Server Bundles GPU, NPU, and Multi-Modal Inference Under One Roof

Lemonade is AMD's open-source local AI server that manages multiple backends like llama.cpp and FastFlowLM across GPU/NPU/CPU, serving text, image, and audio generation through an OpenAI-compatible API.

Scaling Qwen3.5-35B-A3B from 4K to 65K Context with Only 800MB Extra VRAM

Qwen3.5-35B-A3B is an SSM+Attention hybrid where only 10 of 40 layers use KV cache. Expanding ctx-size from 4096 to 65536 on llama-server added just 800MB VRAM with zero speed loss. Includes q8_0 KV quantization benchmarks and TurboQuant status.

Radeon 8060S (gfx1151) Vulkan Broke Again After AMD Driver Update

After updating to AMD Software 26.3.1 on a GMKtec EVO-X2 (Ryzen AI Max+ 395), Vulkan backend fails to allocate device memory properly and falls back to CPU. Investigation and workaround by changing BIOS VRAM allocation from 48GB/16GB to 32GB/32GB.

The Reason Qwen 3.5 Failed on Radeon 8060S Was an Outdated AMD Driver

Isolating the cause of Qwen 3.5 failing on ROCm/Vulkan via CPU inference, llama-server, and LM Studio — an AMD driver update resolved everything.

Abliterated Models in Ollama Were a Complete Failure — and the Official Version Was Fine All Along

All variants of huihui-ai's Qwen 3.5 abliterated produced garbage tokens. GLM-4.7-Flash abliterated had a broken chat template. The official version with thinking disabled turned out to be the right answer.

Optimizing VRAM and Memory Allocation on Strix Halo for Local LLMs

How to configure VRAM/main memory split on the GMKtec EVO-X2 (Strix Halo) for local LLM inference. A 29.6GB model ran fine with just 8GB of dedicated VRAM.

Setting Up a Local LLM on the GMKtec EVO-X2 (Strix Halo)

Building an NSFW-capable local LLM on the GMKtec EVO-X2 (Strix Halo). Getting GPU inference at ~11 tokens/s with LM Studio and MS3.2-24B-Magnum-Diamond.