iapp/openthai2.0-qwen3.8-27b-MLX-4bit

🤗 Hugging Face sourceimage-text-to-textapache-2.027.4B params55 GBsafetensors✓ 5 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo iapp/openthai2.0-qwen3.8-27b-MLX-4bit ./model-folder

Needs a seeder →

OpenThai2.0 - Opensource Thai Knowledge, Document, and Agentic AI (MLX 4-bit)

MLX 4-bit quantization (mlx-vlm) of iapp/openthai2.0-qwen3.8-27b for Apple silicon. Vision included. ~16 GB — runs on 24 GB+ unified memory.

v2.0.3 — rebuilt from the v2.0.3 weights (Thai knowledge-recall fix). The v2.0.0 launch build stays available at revision tag v2.0.0.

Run

pip install mlx-vlm
python -m mlx_vlm generate --model iapp/openthai2.0-qwen3.8-27b-MLX-4bit \
  --image document.jpg --prompt "อ่านข้อความในเอกสารนี้ทั้งหมด" --max-tokens 8192

⚠️ The model reasons before it answers — leave a large generation budget (8k+), or replies may come back empty.

Notes: the MTP draft head is not included (mlx-vlm has no drafter support for this architecture yet). Sanity-verified on-device: Thai factual prompts answered correctly. Full benchmarks and model card: see the main bf16 repo.