Store › model › LLM
POCKET-26B-GGUF
by FINAL-Bench · source Hugging Face · updated 2026-09-25
apache-2.016 GB~19 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-26B-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
- License: apache-2.0
- Requirements: about 19 GB of RAM, 16 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.cppggufconversationalon-devicemobilekoreankorean-llmcpulocal-llmedgegemmagemma4mixture-of-expertsmoepocketvidraft
Numbers
- 296,211 downloads on Hugging Face
- 58 likes
- license apache-2.0
- 16 GB for POCKET-26B-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 21:01 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-26B-Q2_K.gguf | Q2_K | 10 GB |
POCKET-26B-Q4_K_M.gguf | Q4_K_M | 16 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-26B-GGUF · 한국어
A Gemma4-26B-A4B-based pocket model that loads in any app today — Ollama, LM Studio, PocketPal — with no bleeding-edge runtime needed. Korean-tuned, GPU-optional.
> 🚀 Try it live on a CPU (no GPU), no install →
Pick your build → -0f6e56) [](https://hugg…
Source: https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
Card id model:hf:FINAL-Bench/POCKET-26B-GGUF · collected 2026-10-02 21:01 UTC · JSON