README.md

metadata

title: POCKET vs Bonsai · CPU
emoji: ⚔️
colorFrom: yellow
colorTo: green
sdk: docker
app_port: 7860
pinned: true
license: apache-2.0
models:
  - FINAL-Bench/POCKET-35B-GGUF
  - FINAL-Bench/Darwin-36B-Opus
  - prism-ml/Bonsai-27B-gguf
short_description: BONSAI vs POCKET — 35B MoE out-runs the top 1-bit 27B on CPU

BONSAI vs POCKET · live A/B on a CPU

A live demo of POCKET-35B (Q2_K, 13 GB) answering on an upgraded CPU Space — no GPU — with a second tab that races it head-to-head against Bonsai-27B (the most-downloaded 1-bit on-device model) on the same box, same stock llama.cpp. Bonsai answers first, then POCKET — watch the tok/s.

POCKET is a sparse Mixture-of-Experts model (34.66B total, ~3B active/token) quantized from Darwin-36B-Opus. It runs on stock llama.cpp — on a phone, and on a PC with no graphics card.

• 📚 POCKET collection
• 📦 POCKET-35B-GGUF · POCKET-KR-MLX (iPhone) · POCKET-EN-GGUF

Built with FastAPI + llama-cpp-python. Apache-2.0.

---

🧩 The POCKET Family — On-device AI by VIDRAFT

Big models, small hardware. No GPU, no cloud.

Models

• 📦 POCKET-35B-GGUF — flagship, PC / server, no GPU
• 📦 POCKET-26B-GGUF — compact 26B
• 🇰🇷 POCKET-KR-GGUF — Korean, Android
• 🍎 POCKET-KR-MLX — Korean, iPhone / Mac
• 🌍 POCKET-EN-GGUF — English, phone / PC
• 🖼️ POCKET-Image-Zimage — character-perfect text in any image

Demos & tools (Spaces)

• 🎨 POCKET-Image Studio — text-in-image, generate in-page
• 🖥️ POCKET-35B-CPU — 35B answering on a CPU
• 🖥️ POCKET-26B-CPU — 26B on a CPU

📚 Full POCKET collection