{"v":1,"id":"model:hf:FINAL-Bench/POCKET-26B-GGUF","slug":"model-final-bench-pocket-26b-gguf","kind":"model","category":"llm","title":"POCKET-26B-GGUF","summary":"🆕 POCKET-Qwen3.8-Flash-Next — a 180B model running on a laptop with 8 GB VRAM + 32 GB RAM · 4.17 tok/s measured. >","source":{"provider":"hf","ref":"FINAL-Bench/POCKET-26B-GGUF","url":"https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF","rev":"1f9ee555b16b9835a623fbc64dff4f6166ef3741","fetchedAt":"2026-10-02T21:01:09.622Z","etag":"W/\"96e-0+YR/MBUuXhWLRxHgJawCIGLrv0\""},"author":{"name":"FINAL-Bench","url":"https://huggingface.co/FINAL-Bench"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":296211,"downloadsWeek":327838,"likes":58,"takenAt":"2026-10-02T21:01:09.622Z"},"tags":["llama.cpp","gguf","conversational","on-device","mobile","korean","korean-llm","cpu","local-llm","edge","gemma","gemma4","mixture-of-experts","moe","pocket","vidraft","text-generation","endpoints_compatible","imatrix"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-09-25T12:47:14.000Z","collectedAt":"2026-10-02T21:01:09.622Z","review":{"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"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:09.622Z","http":200},"description":"> ### 🆕 **[POCKET-Qwen3.8-Flash-Next](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF)** — a **180B** model running on a **laptop with 8 GB VRAM + 32 GB RAM** · **4.17 tok/s measured**.\n> [](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF) []() []() []()\n\n> ### 🆕 **[POCKET-Zimage-CPU](https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU)** — photoreal **images** in **46 s** on a **CPU only**. No GPU, no CUDA, no Python.\n> [](https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU) [](https://huggingface.co/spaces/FINAL-Bench/POCKET-Zimage-CPU) []()\n\n> ### 📚 Collections\n> **▶ [POCKET Models](https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6)** — this family (on-device, no GPU)\n> [Darwin Family](https://huggingface.co/collections/FINAL-Bench/darwin-family-699987b1f652864af0122193) · [Aether Foundation](https://huggingface.co/collections/FINAL-Bench/aether-foundation-model-6a5c7f2fa1a4165c0414e53a) · [VKAE Accelerated](https://huggingface.co/collections/FINAL-Bench/vkae-accelerated-6a47231d7e7999dd8227675a)\n\n# POCKET-26B-GGUF · 한국어\n\n### 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.\n\n> 🚀 **Try it live on a CPU (no GPU), no install →** [](https://huggingface.co/spaces/FINAL-Bench/POCKET-26B-CPU) [](https://huggingface.co/spaces/FINAL-Bench/POCKET-35B-CPU)\n\n[](https://www.apache.org/licenses/LICENSE-2.0) [](https://github.com/ggml-org/llama.cpp) []() [](https://huggingface.co/google/gemma-4-26B-A4B-it)\n\n**Pick your build →** [](https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF) [](https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF) [](https://huggingface.co/FINAL-Bench/POCKET-KR-GGUF) [-0f6e56)](https://huggingface.co/FINAL-Bench/POCKET-KR-MLX) [](https://huggingface.co/FINAL-Bench/POCKET-EN-GGUF) [](https://hugg…\n\nSource: https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF","install":{"kind":"model","hfId":"FINAL-Bench/POCKET-26B-GGUF","gated":false,"format":"gguf","files":[{"name":"POCKET-26B-Q2_K.gguf","size":11123718688,"quant":"Q2_K","sha256":"490687be6493769dc8322df396cd31d412a15877eaccea4d2f16ca1f93383334"},{"name":"POCKET-26B-Q4_K_M.gguf","size":16795998752,"quant":"Q4_K_M","sha256":"b91b0923605621d246fdcce733d3666020273cf7abaf172dd5345659c96aab1b"}],"totalBytes":27919717440,"suggestedFile":"POCKET-26B-Q4_K_M.gguf","requirements":{"ramGb":19,"diskBytes":16795998752,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"],"command":"lsh models install hf:FINAL-Bench/POCKET-26B-GGUF"}}