aac-board-generator-moe-636m-ptbr —
a sovereign Mixture-of-Experts model that generates and edits AAC pictogram boards in Brazilian Portuguese,
running fully on CPU via llama.cpp. Built for Papuguinho.k: ≈141M (k=1) · ≈212M (k=2, default) · ≈283M (k=3).⚠️ Requires allama.cppbuild with the customgemma3moearchitecture. The stock upstream build does not yet include it.
--override-kv needed):
k = active experts (1 = ≈2× faster · 2 = best quality) × quant (Q4 → Q8, smaller → higher fidelity).
Weights are identical across k; only runtime routing differs.| Quant | Size | k=1 · fast (≈210 tok/s) | k=2 · best (≈90–130 tok/s) |
|---|---|---|---|
| Q4_K_M | 460 MB | aac-moe-636m-v2-k1-Q4_K_M.gguf | aac-moe-636m-v2-k2-Q4_K_M.gguf |
| Q5_K_M | 496 MB | aac-moe-636m-v2-k1-Q5_K_M.gguf | aac-moe-636m-v2-k2-Q5_K_M.gguf |
| Q6_K | 632 MB | aac-moe-636m-v2-k1-Q6_K.gguf | aac-moe-636m-v2-k2-Q6_K.gguf |
| Q8_0 | 681 MB | aac-moe-636m-v2-k1-Q8_0.gguf | aac-moe-636m-v2-k2-Q8_0.gguf |
| f16 | 1.2 GB | aac-moe-636m-v2-k1-f16.gguf | aac-moe-636m-v2-k2-f16.gguf |
k1-Q4_K_M (460 MB) — quality verified OK on both board generation and edit commands.k2-Q8_0 (681 MB).k1-Q5_K_M or k2-Q5_K_M.1# Board generation
2llama-cli -m aac-moe-636m-v2-k1-Q4_K_M.gguf --jinja \
3 -sys "$(cat corpo_chatbot.txt)" \
4 -p "quero uma prancha de escola" -n 200 -st
5
6# Ask for a specific count
7# -p "gera 5 pictogramas de praia"
8
9# Board editing (agent) — pass the current board + a command, use corpo_comando.txt as system promptlabel|category|search_terms. Edit commands return a compact DSL
(R| confirm, +| add, -| remove, T| retitle, C| columns, X| new theme).