hugpadhugpad

FINAL-Bench / POCKET-EN-GGUF

Text Generation34852Updated Sep 25, 2026
Hugging Face

Downloads

348

Likes

52

Last updated

Sep 25, 2026

License

apache-2.0

### 🆕 POCKET-Qwen3.8-Flash-Next — a 180B model running on a laptop with 8 GB VRAM + 32 GB RAM · 4.17 tok/s measured. ![New](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF) ![VRAM]() ![RAM]() ![Speed]() <!-- POCKET-FLASHNEXT-BADGE --

Tasks & library

  • text generation
  • llama.cpp

Tags

  • llama.cpp
  • gguf
  • conversational
  • on-device
  • mobile
  • iphone

Technical specifications

ParametersNot available
Libraryllama.cpp
LanguagesNot available
Base modelFINAL-Bench/Darwin-36B-Opus
Licenseapache-2.0