GitSeonjeap
English

Sign in

Reading needs no sign-in. Sign in to write posts or comments, or to recommend and report, in the community.

By signing in you agree to the notices below. Community rules · Privacy notice

Keep browsing without signing in

Blog

Written versions of our YouTube videos, so you can check the numbers and tables at your own pace.

  1. MacBook Air M6 Release Date: March 2027? Mac Schedule Predicted from Six Years of Records (youtube.com)

    The MacBook Air M6 most likely arrives in March 2027. Six years of Apple silicon Mac announcements give release rules by line and an estimated next schedule. Not an Apple announcement; it may be wrong.

  2. Flint on a Mac mini 32GB: 5 Engines at 52.4-76.0 tok/s vs Qwen (youtube.com)

    We ran Flint on a Mac mini M6 32GB with five engines: 52.4 to 76.0 tokens per second, not purely an engine difference. In coding-agent runs Qwen passed 15 and Flint 12.

    |Video released #Flint#Recursive Flint#Mac mini#local AI
  3. Mac mini 32GB Local AI Engines: Splash JSON 69.3 vs 8.5 Baseline Tokens (youtube.com)

    Eight local AI engines measured on a Mac mini M6 32GB with the same questions: big gains for English, code and JSON, smaller for Korean. Speed only; not purely the engine.

    |Video released #Mac mini#local AI#engine comparison#Splash
  4. Will It Run on My PC? Quantized Files 5 to 94GB: RAM, VRAM and Mac Fit (youtube.com)

    Lower quantization shrinks Qwen 27B from 17.56 to 10.52GB on a 32GB Mac mini and speeds Korean from 8.2 to 13.0 tok/s. When a file exceeds RAM, speed collapses. 3090, 5090 and Mac fit, with October 15 prices.

    |Video released #quantization#local LLM#VRAM#RAM
  5. GLM-5.3 Flash vs Qwen 3.8 Flash-Next Benchmark: Mac mini 32GB and RTX PRO 6000 (youtube.com)

    We measured GLM-5.3 Flash and Qwen 3.8 Flash-Next at the same 4-bit on a Mac mini 32GB and two servers: will it run, speed, and 40 Korean questions, with measurements and estimates kept apart.

    |Video released #GLM-5.3#Qwen 3.8#Flash-Next#Mac mini
  6. Mac mini M6 AI Image: 3 min 20 s to 2 min 20 s, Qwen-Image 2.1 Measured (youtube.com)

    On a Mac mini M6 32GB, Qwen-Image 2.1 took 3 min 20 s in default ComfyUI, about 2 min 20 s with just the model file switched to bf16, and about 2 min with mflux 4-bit. Korean text accuracy and memory picks included.

    |Video released #Mac mini#Mac mini M6#Qwen-Image#ComfyUI
  7. Mac mini M6 Without a Subscription: Voice Cloning, Music and Transcription, 8 Local AIs vs Paid (youtube.com)

    On a Mac mini M6 32GB we tested eight local AIs for voice cloning, music and transcription against paid services: VoxCPM2 similarity 0.918, Suno lyric error 2.3%, Whisper error 3.6%.

    |Video released #Mac mini#Mac mini M6#voice cloning#VoxCPM2