Hands-on log of building the DEV article's PDF RAG on M1 Max 64GB, extending it with images via CLIP, and pushing through Japanese with bge-m3 + Qwen3.6 35B. Documents the modality gap, the dual inference server crash, and LLM-jp 4-8B's empty chat template silently dropping the system role.
Notes on a DEV Community article that wires up FastAPI as an OpenAI-compatible RAG API layer with llama.cpp, Chroma, and Open WebUI, plus where the architecture fits and what to watch for.
A read of arXiv:2604.26622 OCR-Memory. It renders agent execution history into images, uses Set-of-Mark to let a VLM pick relevant segments, then retrieves verbatim text from the original logs.
A hands-on log of running Qwen-Scope's Sparse Autoencoder locally on M1 Max 64GB with Qwen3-8B-Base, extracting feature IDs that discriminate between Japanese, English, code, and Chinese from a single middle layer.
The Qwen team released Qwen-Scope, a Sparse Autoencoder suite for Qwen3/Qwen3.5. 14 groups of SAEs covering inference-time steering, evaluation analysis, toxicity classification, data synthesis, and training improvement.
NII/LLMC released CC Audio and Archive.org Audio Dataset. URL lists, metadata, and a downloader covering 48,000+ hours of Japanese audio. What it actually contains and how it fits into TTS, ASR, and audio model training.
Pruna AI's FP8 speedup needs compute capability 8.9, so Apple Silicon is out. Measured what M1 Max 64GB actually does with MLX-based mflux and antirez's iris.c: install traps, real generation times, and a wrapper kit to skip the setup.
Designing field-level confidence thresholds for human-in-the-loop document extraction, and the OCR and threshold walls hit when automating journal entries with freee MCP.
After Xiaomi MiMo-V2.5's weights went public, I checked whether it runs on Mac/ROCm or on cloud GPU (RunPod/GCE). It's still rough on local hardware, but RunPod's 4x H200 runs it for ~$14/hr and GCE Spot H100 brings it down to ~$1.6/hr.
SeeSee21/Z-Anime is a full fine-tune of Z-Image Base (S3-DiT, 6B) — not a LoRA merge. Ran the AIO build on local ComfyUI (M1 Max 64GB): working t2i and i2i settings for Base vs Distill 8/4-step, GGUF options, and what NSFW prompts actually pass.
A verification log for converting color anime-style AI illustrations to manga-style monochrome. AI re-generation approaches lean to either color leakage or face drift, and pure deterministic local processing looks mechanical. Frames the next directions to try: putting a grayscale-only LoRA on Anima, and using See-through for part decomposition before mechanical composition.
SB Intuitions released sarashina2.2-tts, an LLM-based TTS model focused on Japanese. It clones speaker voice and style from short reference audio without fine-tuning, and handles Japanese-English code-switching.
