FINAL-Bench / POCKET-KR-GGUF

huggingface.co
Total runs: 995
24-hour runs: 7
7-day runs: 477
30-day runs: 808
Model's Last Updated: September 25 2026
text-generation

Introduction of POCKET-KR-GGUF

Model Details of POCKET-KR-GGUF

๐Ÿ“š Collections

โ–ถ POCKET Models โ€” this family (on-device, no GPU) Darwin Family ยท Aether Foundation ยท VKAE Accelerated ยท Metacognition Adapters

POCKET

POCKET-KR-GGUF ยท ํ•œ๊ตญ์–ด

35B์—์„œ ํ•œ๊ตญ์–ด ์ „๋ฌธ๊ฐ€๋งŒ ๊ณจ๋ผ๋‚ธ ํฐ์šฉ ๋นŒ๋“œ. Android 8 GB+์—์„œ GPU ์—†์ด ๋•๋‹ˆ๋‹ค. iPhone์€ POCKET-KR-MLX ๋ฅผ ๋ฐ›์œผ์„ธ์š”.

๐Ÿš€ Try it live, no install โ†’ Live demo โ€” a 35B model answering on a CPU-only box.

License Runtime No GPU Base

Pick your build โ†’ 35B KR GGUF KR MLX EN GGUF

The POCKET lineup โ€” pick by your device
Repo File Size Runs on Best for Korean PPL*
POCKET-35B-GGUF Q4_K_M 21 GB PC / server (32 GB RAM) top quality 5.79
POCKET-35B-GGUF Q2_K โญ 13 GB mini-PC, no GPU daily driver 6.49
POCKET-35B-GGUF IQ1_M 8.2 GB 16 GB RAM box smallest full model 9.69
POCKET-KR-GGUF IQ2_M 5.1 GB Android 8 GB+ ๐Ÿ‡ฐ๐Ÿ‡ท Korean phone 7.95
POCKET-KR-MLX 2-bit 5.1 GB ๐ŸŽ iPhone / iPad / Mac ๐Ÿ‡ฐ๐Ÿ‡ท Korean, Apple-native 7.95
POCKET-EN-GGUF iPhone-mix 5.3 GB ๐ŸŽ iPhone (PocketPal) ๐ŸŒ English phone โ€”
POCKET-EN-GGUF PC-mix 6.8 GB PC / Android ๐ŸŒ English, best quality โ€”

*Wikipedia-Korean perplexity, lower is better. Q4_K_M = 5.79 baseline. English builds are tuned on English; see each repo.

๐ŸŽ Why MLX for Korean but GGUF for English on iPhone? Apple-native MLX only does uniform quantization. Korean survives it (96 experts hold up); English needs our mixed-precision trick, which only GGUF supports โ€” so the English iPhone build ships as a GGUF you run with PocketPal . Honest, not lazy.

Speed vs Bonsai

Benchmarks โ€” what is measured, what is not

We measure Bonsai on the same machine with the same stock llama.cpp , and we tell you where we lose.

[measured] Generation speed โ€” POCKET wins on both CPU and GPU:

POCKET-35B IQ1_M Bonsai-27B Q1_0
CPU generate (Xeon, 16t) 27.0 tok/s 10.1 ๐ŸŸข 2.69ร—
GPU generate (H100) 197 tok/s 89 ๐ŸŸข 2.22ร—
GPU prompt (H100) 753 1816 ๐Ÿ”ด 0.41ร—
Quality (HellaSwag, 400q) 61.0% 60.0% โšช tie (CI overlaps)

[measured on a MacBook M3 Pro, 18 GB] โ€” and on a laptop, POCKET wins every axis, including prompt processing:

POCKET-35B IQ1_M Bonsai-27B Q1_0
Metal generate (tg64) 25.4 tok/s 12.8 ๐ŸŸข 1.99ร—
CPU generate (8 threads) 13.8 tok/s 4.4 ๐ŸŸข 3.13ร—
Metal prompt (pp128) 240.7 tok/s 73.4 ๐ŸŸข 3.28ร—
CPU prompt (pp128) 45.5 tok/s 9.6 ๐ŸŸข 4.75ร—

On a laptop GPU the arithmetic headroom that let Bonsai win prefill on an H100 is gone, so MoE sparsity wins across the board. POCKET-35B-Q2_K runs on the M3 Pro's CPU at 19.5 tok/s โ€” on an 18 GB Mac, run Q2_K on CPU ( -ngl 0 ); its 13 GB exceeds the recommended Metal budget.

[pending โ€” community reports welcome] on-device iPhone and Strix Halo throughput. We publish only what we ran ourselves; help us fill the rest.

The same-size rival Ternary-Bonsai-27B-Q2_0 (7.2 GB) fails to load in upstream llama.cpp โ€” it needs the PrismML fork. POCKET runs on the tools you already have.

Files in this repo
File Size Experts Runs on Korean PPL
POCKET-KR-IQ2_M.gguf โญ 5.1 GB 96 Android 8 GB+ 7.95
POCKET-KR-160-Q2_K.gguf 8.5 GB 160 phone/PC 6.88 (quality-first)
POCKET-KR-160-Q3_K_M.gguf 11 GB 160 PC 6.35

Pruned from 256 experts to the ones Korean actually uses (94% routing coverage at 128). Active params unchanged โ†’ same speed, half the size.

Quickstart
llama-cli -m POCKET-KR-IQ2_M.gguf -p "๋Œ€ํ•œ๋ฏผ๊ตญ์˜ ์ˆ˜๋„๋Š”" -ngl 0 -t 8

On Android: PocketPal โ†’ import GGUF.

Lineage โ€” where POCKET comes from

POCKET is quantized from Darwin-36B-Opus , VIDRAFT's flagship โ€” a model bred and evolved over several generations on the Darwin platform (crossbreeding, healing, expert surgery). Darwin-36B-Opus itself traces back to a Qwen3.5-family MoE architecture.

Component Origin
Starting checkpoint Darwin-36B-Opus โ€” VIDRAFT, multi-generation Darwin evolution
Base architecture Qwen3.5-family MoE (256 experts, top-8), unchanged
Quantization ( Q4_K_M โ€ฆ IQ1_M ) stock llama.cpp โ€” no custom format
Runtime upstream llama.cpp / Apple MLX โ€” unmodified
Expert pruning + domain imatrix (KR/EN builds) ours (VIDRAFT)

The CPU/GPU speed comes from the sparse-MoE architecture plus ordinary quantization โ€” reproducible with the same base and the same tools. What we add is the Darwin-evolved weights, the honest measurement, the Korean tuning, and the pruning that makes the 5 GB phone builds.

Limitations
  • The iPhone/Mac speed is not yet measured by us โ€” community reports welcome.
  • Extreme quants ( IQ1_M ) hurt Korean ~2.8ร— more than English; use Q2_K or larger for quality.
  • English phone builds trade quality for size; the PC build ( PC-mix ) is much closer to full quality.
License

Apache-2.0.


POCKET is a VIDRAFT model family. 35B, in your pocket. No GPU.

Runs of FINAL-Bench POCKET-KR-GGUF on huggingface.co

995
Total runs
7
24-hour runs
8
3-day runs
477
7-day runs
808
30-day runs

More Information About POCKET-KR-GGUF huggingface.co Model

More POCKET-KR-GGUF license Visit here:

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

POCKET-KR-GGUF huggingface.co

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

FINAL-Bench POCKET-KR-GGUF online free

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

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

https://huggingface.co/FINAL-Bench/POCKET-KR-GGUF

POCKET-KR-GGUF install

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

POCKET-KR-GGUF install url in huggingface.co:

https://huggingface.co/FINAL-Bench/POCKET-KR-GGUF

Url of POCKET-KR-GGUF

POCKET-KR-GGUF huggingface.co Url

Provider of POCKET-KR-GGUF huggingface.co

FINAL-Bench
ORGANIZATIONS

Other API from FINAL-Bench