FINAL-Bench / POCKET-26B-GGUF

huggingface.co
Total runs: 271.4K
24-hour runs: 0
7-day runs: -33.3K
30-day runs: -61.7K
Model's Last Updated: Septembre 25 2026
text-generation

Introduction of POCKET-26B-GGUF

Model Details of POCKET-26B-GGUF

📚 Collections

▶ POCKET Models — this family (on-device, no GPU) Darwin Family · Aether Foundation · VKAE Accelerated · Metacognition Adapters

POCKET-26B

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 → POCKET-26B demo POCKET-35B demo

License Runtime Compat Base

Pick your build → 35B KR GGUF KR MLX EN GGUF

Why this one?

POCKET-26B takes Google's Gemma4-26B-A4B (25.2B total, ~4B active MoE, Apache-2.0) and re-quantizes it with our proprietary Korean-tuned quantization — unpruned , so quality holds. Unlike our Qwen-based POCKET (which needs a very recent llama.cpp build for its qwen35moe architecture), Gemma4 loads in every mainstream runtime today : Ollama, LM Studio, PocketPal, koboldcpp, and the browser.

Quality — GPQA-Diamond, greedy, 198 questions (our harness)
Build GPQA-Diamond vs base
Gemma4-26B-A4B (base) 67.7% —
POCKET-26B Q4_K_M 67.7% = base (lossless)
POCKET-26B Q2_K (mixed) ⭐ 67.2% −0.5pp (≈ lossless)

Single greedy pass, 198 items → ±~3 pp noise. Our proprietary Korean-tuned quantization is statistically lossless vs the base.

Files in this repo
File Size Runs on Best for
POCKET-26B-Q4_K_M.gguf 17 GB PC / high-RAM top quality
POCKET-26B-Q2_K.gguf ⭐ 11 GB 12 GB phone / PC / browser universal daily driver

Our mixed-precision quantization keeps the most quality-critical weights at higher precision — that is why Q2_K holds 67.2% while a plain uniform Q2 collapses to ~44%.

Quickstart — loads anywhere
# stock llama.cpp — brew / winget / apt, or LM Studio / Ollama / PocketPal
llama-cli -m POCKET-26B-Q2_K.gguf -p "대한민국의 수도는?" -ngl 0 -t 8

No fork, no bleeding-edge build — Gemma4 support has shipped in every mainstream runtime since April 2026.

Lineage (honest)

Based on google/gemma-4-26B-A4B-it (Apache-2.0). We do not re-host it unchanged — we add our proprietary Korean-tuned quantization (VIDRAFT). We deliberately do not prune it: Gemma4's low-bit robustness collapses under pruning (measured), so we keep all 128 experts and win on quality + universal compatibility instead.

Limitations
  • For 8 GB phones (~5 GB budget), use POCKET-KR-GGUF (5.1 GB) — Gemma4 cannot be shrunk that far without collapse.
  • On-device iPhone/Mac throughput not yet measured by us — community reports welcome.
Learn more
License

Apache-2.0 — use, modify, redistribute freely.


POCKET is a VIDRAFT model family. Runs anywhere, no GPU.

Runs of FINAL-Bench POCKET-26B-GGUF on huggingface.co

271.4K
Total runs
0
24-hour runs
0
3-day runs
-33.3K
7-day runs
-61.7K
30-day runs

More Information About POCKET-26B-GGUF huggingface.co Model

More POCKET-26B-GGUF license Visit here:

https://choosealicense.com/licenses/apache-2.0

POCKET-26B-GGUF huggingface.co

POCKET-26B-GGUF huggingface.co is an AI model on huggingface.co that provides POCKET-26B-GGUF's model effect (), which can be used instantly with this FINAL-Bench POCKET-26B-GGUF model. huggingface.co supports a free trial of the POCKET-26B-GGUF model, and also provides paid use of the POCKET-26B-GGUF. Support call POCKET-26B-GGUF model through api, including Node.js, Python, http.

FINAL-Bench POCKET-26B-GGUF online free

POCKET-26B-GGUF huggingface.co is an online trial and call api platform, which integrates POCKET-26B-GGUF's modeling effects, including api services, and provides a free online trial of POCKET-26B-GGUF, you can try POCKET-26B-GGUF online for free by clicking the link below.

FINAL-Bench POCKET-26B-GGUF online free url in huggingface.co:

https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF

POCKET-26B-GGUF install

POCKET-26B-GGUF is an open source model from GitHub that offers a free installation service, and any user can find POCKET-26B-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of POCKET-26B-GGUF install, users can directly use POCKET-26B-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

POCKET-26B-GGUF install url in huggingface.co:

https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF

Url of POCKET-26B-GGUF

POCKET-26B-GGUF huggingface.co Url

Provider of POCKET-26B-GGUF huggingface.co

FINAL-Bench
ORGANIZATIONS

Other API from FINAL-Bench