POCKET-35B
A 35B model that out-runs the top 1-bit 27B — on a CPU, no GPU.
Sparse Mixture-of-Experts · ~3B active per token · same stock llama.cpp, side by side
34.66B total ~3B active/token 0 GPU Q2_K · 13 GB
starting…
🌳 Bonsai-27B 1-bit dense · runs first
📦 POCKET-35B sparse MoE · runs second
Type a prompt — Bonsai answers first, then POCKET on the same CPU.

What am I looking at?

The exact same prompt is sent to Bonsai-27B (the most-downloaded on-device model, a 1-bit dense build) and to POCKET-35B (our sparse Mixture-of-Experts, Q2_K) — on the same CPU-only box, the same stock llama.cpp. Bonsai runs first, then POCKET. Watch the tok/s on each side.

Why POCKET wins on generation: a dense 27B reads all of its weights every token (~3.5 GB); POCKET's MoE wakes only ~3B parameters (~0.7 GB). The weaker the hardware, the wider the gap.

Honest notes: sequential race, each model gets the full CPU. tok/s is llama.cpp's measured generation speed. On a shared box a dedicated machine is faster. Prompt processing (not shown) is one place Bonsai leads on very long inputs. Quality is a statistical tie. Bonsai is a trademark of its owners; shown here for factual comparison only.