Hands-on with Tencent Hy-MT2 1.8B Q4_K_M (1.08GB) on M1 Max 64GB via llama-server. JSON, SRT, HTML, glossary, and minority-language prompts with full input-output pairs. The 1.25bit 440MB build does not load on stock llama.cpp 8990, and 30B-A3B (hy_v3) is not in the Mac route yet.
Ran WAI-Anima v1.0 with a custom character LoRA on an M1 Mac to see if 2- and 3-character compositions actually hold up. Notes on what breaks and what holds at different LoRA weights, with practical settings that stay stable.
Tested on M1 Max 64GB ComfyUI: SetLatentNoiseMask silently fails on Anima + Anima-Turbo. LanPaint runs Example_26 in 32 min/image; Inpaint-CropAndStitch drops that to 2:31 for text inpaint and ~7 min for clothing replacement.
Tested on M1 Max: Floyd-Steinberg halftone + BLE pacing + a vendor-specific density command `1D 49 F0 nn` to print sharp photos on the Sugar YMP-01 thermal mini printer from Python.
Tested on M1 Max: switching a Python BLE client to RFCOMM (SPP Ch.2) cuts transfer from ~60s to 5.38s for a 140KB JPEG. Covers PyObjC quirks, macOS Bluetooth entitlement, and an isolation experiment confirming olie.xdev's 'possibly not required' steps.
Tested Klein 9B + 9B NSFW LoRA on M1 Max 64GB via mflux 0.17.5: 1m51s/512, 5m37s/1024 q4, 224/224 LoRA keys match, NSFW prompts uncensored, Japanese subjects work with helper tokens.
Klein 4B / 9B / Base LoRAs aren't cross-compatible — a 9B NSFW LoRA throws 'lora key not loaded' on mflux's 4B path. The variant map, what mflux runs today, and where the working hands-on test lives.
Three local image generation engines (WAI-Anima, WAI-IL/SDXL, FLUX.2 Klein 4B) tied together by a thin FastAPI wrapper that takes Japanese prompts. Ollama (gemma3:12b) handles JP→EN, ComfyUI workflows are built on the fly in Python, FLUX.2 runs as an mflux subprocess, and the whole thing is reachable from an iPhone over Tailscale.
Hands-on benchmark of FLUX.2 Klein 4B on M1 Max 64GB using mflux (MLX) and iris.c (pure C + Metal). A counter to Pruna AI's H100-only tutorial — measuring how fast Apple Silicon actually gets there.
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.
Went 0-for-13 trying to train an Illustrious-XL LoRA on a Mac Studio M1 Max 64GB. With help from multiple AI agents, pinpointed the root causes and finally succeeded on a RunPod RTX 4090. The full record: three fatal parameters and the sd-scripts trap.
