Store › model › LLM

POCKET-35B-GGUF

Name: POCKET-35B-GGUF
Author: FINAL-Bench

by FINAL-Bench · source Hugging Face · updated 2026-09-25

apache-2.020 GB~24 GB RAMsource aliveunlabeled

🆕 POCKET-Qwen3.8-Flash-Next — a 180B model running on a laptop with 8 GB VRAM + 32 GB RAM · 4.17 tok/s measured. >

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:FINAL-Bench/POCKET-35B-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF
License: apache-2.0
Requirements: about 24 GB of RAM, 20 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
Tags: llama.cpp gguf conversational on-device mobile iphone android cpu local-llm edge mixture-of-experts moe quantized pocket vidraft qwen3_5_moe

Numbers

669,265 downloads on Hugging Face
81 likes
license apache-2.0
20 GB for POCKET-35B-Q4_K_M.gguf
327,838 npm downloads a week for node-llama-cpp
latest node-llama-cpp@3.22.1

Numbers as of 2026-10-02 20:59 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`POCKET-35B-IQ1_M.gguf`	IQ1_M	7.7 GB
`POCKET-35B-Q2_K.gguf`	Q2_K	12 GB
`POCKET-35B-Q3_K_M.gguf`	Q3_K_M	16 GB
`POCKET-35B-Q4_K_M.gguf`	Q4_K_M	20 GB

From the source README

> ### 🆕 POCKET-Qwen3.8-Flash-Next — a 180B model running on a laptop with 8 GB VRAM + 32 GB RAM · 4.17 tok/s measured.
>

> ### 🆕 POCKET-Zimage-CPU — photoreal images in 46 s on a CPU only. No GPU, no CUDA, no Python.
>

> ### 📚 Collections
> ▶ POCKET Models — this family (on-device, no GPU)
> Darwin Family · Aether Foundation · VKAE Accelerated

POCKET-35B-GGUF

A 35B model that runs on your PC with no GPU — and on your phone. Just stock `llama.cpp`. No fork, no CUDA, no cloud.

> 🚀 Try it live, no install → — both answering on a CPU-only box (no GPU). POCKET-26B is Gemma4-based.

Pick your build → -0f6e56) [](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Fl…

Source: https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF

Card id model:hf:FINAL-Bench/POCKET-35B-GGUF · collected 2026-10-02 20:59 UTC · JSON