#Local LLM

H Company's Holotron-12B uses a memory-efficient new design to lift PC-operation AI throughput to 8,900 tokens per second. Unsloth has released the beta of 'Studio,' a browser tool for no-code model fine-tuning.

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.

Hands-on test of huihui-ai Qwen 3.5 abliterated models in Ollama: garbage-token failures, GLM-4.7-Flash chat-template breakage, and why the official model with thinking disabled worked better.

A folder-watching script that automatically OCRs images scanned by ScanSnap and runs LLM-based correction. Includes air-gap security design.

From Docker hell to Lite + LLM correction. A retrospective on my own experimentation, plus an introduction to someone else's browser-based NDLOCR-Lite implementation.

Set up the CLI version of NDLOCR-Lite on Apple Silicon Mac, then tested OCR result correction with Qwen 3.5 and Swallow. Includes experiments with direct image reading and the anchoring effect.

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.

ACE-Step V1.5 has been released with a hybrid LM+DiT architecture, 50+ language support, and 4GB VRAM minimum — a major evolution from V1.0.