📚 Collections

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

POCKET-EN-GGUF · English

English-focused pocket build using our proprietary quantization — protects the quality-critical layers so quality holds at 5 GB. Runs on iPhone (PocketPal) and any CPU PC. No fork.

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

Pick your build →

The POCKET lineup — pick by your device

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

🍎 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 proprietary quantization, which only GGUF supports — so the English iPhone build ships as a GGUF you run with PocketPal. Honest, not lazy.

🆕 POCKET-26B — a Gemma4-26B-A4B-based sibling that loads in any app today (Ollama · LM Studio · PocketPal · MLX), no bleeding-edge runtime needed: GGUF (Q2_K 11 GB · Q4_K_M 17 GB · GPQA-Diamond 67%). Universal compatibility for 12 GB phones, PC, and browser.

Benchmarks — 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 — POCKET wins on both CPU and GPU:

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

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 — on an 18 GB Mac, run Q2_K on CPU (-ngl 0); its 13 GB exceeds the recommended Metal budget.

[measured — GPQA Diamond, 198q, greedy] reasoning quality vs quantization:

[pending — 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 — it needs the PrismML fork. POCKET runs on the tools you already have.

Files in this repo

Our proprietary mixed-precision quantization protects the most quality-critical weights — which is why English quality holds at this size.

Quickstart

llama-cli -m POCKET-EN-PC-mix.gguf -p "Explain mixture-of-experts in one line." -ngl 0 -t 8

Lineage — where POCKET comes from

POCKET is quantized from Darwin-36B-Opus, VIDRAFT's flagship — 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.

The CPU/GPU speed comes from the sparse-MoE architecture plus ordinary quantization — 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 — community reports welcome.
• Extreme quants (IQ1_M) hurt Korean ~2.8× 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.

Learn more

• On-device LLMs without a GPU — and how POCKET measures up: Can you run a large LLM without a GPU?
• What model quantization is, and why a 4-bit model stays smart: What is model quantization?