My ModelScope account switched from a monthly API-Inference quota to Magicube coins, so I measured what each call costs. Qwen-Image, Z-Image, Krea-2-Turbo and FLUX worked even though none of them appeared in the /v1/models list I got; of the embedding IDs I tried only Qwen3-Embedding went through; audio paths were 404 and Wan produced no video. In these tests 400s and 404s cost nothing, while a 200 with an empty body was charged.
Tested on EVO-X2 (gfx1151) under Windows + ROCm: the official b10666 binary runs it at pp512 159.25 / tg128 23.26, and the earlier crash was my own workaround flag.
On an M4 Mac mini (Codex 0.150.1), stdio MCP servers keep the controlling terminal, so a child reading the tty SIGTTIN-stops the CLI. Shell tools got setsid; MCP didn't.
Tested on M1 Max 64GB: AtomicChat's M64 GGUF keeps the 51B N-gram table in its own shard, so a llama.cpp PR #27742 build leaves it on SSD and runs the 125B MoE at 17.6 tok/s.
Tested on M1 Max 64GB, ComfyUI v0.30.1: i2i and Qwen-Image-Edit lost the character, so I rebuilt the pose one prompt at a time, plus why negatives do nothing at cfg 1.0.
Tested on M1 Max 64GB, ComfyUI v0.33.3: from-behind and a back-row drummer now pass, out-of-frame crops get worse, and Anima-Base LoRAs need a 52-block key remap.
Tested on M1 Max 64GB with MLX: LLaMA Pro-style block expansion on Qwen3-0.6B-Base vs LoRA vs full FT, trained on 722 blog posts. Held-out PPL drops 14.7 to 10.5, but Wikipedia-ja rises 13.5 to 17.9, more forgetting than full FT. A 20% Wikipedia mix nearly removes it, and renumbering 28-layer LoRA keys reproduces the Anima-2.9B result in numbers.
16GB M4 Mac mini test of QwenLM's Qwen-MM-Plugins core. Claude Code adds a plugin_ prefix that breaks --allowedTools, codex exec rejects MCP calls by default. PDF, STL and video read with no API key.
A three-instruction leap-year test hides the constants 1073750999, 3221352463, and 126976. I rebuilt an 18-bit version with Z3, then traced how the multiply, mask, and threshold encode divisibility by 4, 100, and 400.
Tested on M1 Max 64GB, ComfyUI v0.33.3. Anima-2.9B inserts 12 DiT blocks, so Anima-Base LoRA keys hit the wrong layers with zero warnings, 0/3. Renumbering the keys gives 3/3.
Benchmarked on an M4 Mac mini: Ben Joffe's 2-instruction weekday hack beats plain %7 by 1.6-6.4x in clang, Rust, and V8, loses 3x in CPython. Plus a 25x V8 -0 deopt trap.
Tested on GMKtec EVO-X2 (Ryzen AI Max+ 395): Q8_0 + MTP beats a 4-bit M1 Max at 22 tok/s, thinking burns 32,712 chars before any HTML, and the NSFW refusal line moves.
