Store › model › Embeddings
aac-pictogram-retriever-ptbr-GGUF
by Papuguinho · source Hugging Face · updated 2026-08-08
gemma104 MB~1 GB RAMsource aliveunlabeled
GGUF quantizations of Papuguinho/aac-pictogram-retriever-ptbr for use with llama.cpp.
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:Papuguinho/aac-pictogram-retriever-ptbr-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/Papuguinho/aac-pictogram-retriever-ptbr-GGUF
- License: gemma (restricted license: terms at the source apply)
- Requirements: about 1 GB of RAM, 104 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
- Tags:
ggufsentence-similarityembeddingsretrievalrerankingsemantic-searchaacaugmentative-alternative-communicationarasaacpictogramsportuguesebrazilian-portuguesecpullama.cppptendpoints_compatible
Numbers
- 2,468 downloads on Hugging Face
- 0 likes
- license gemma
- 0.1 GB for aac-Q4_K_M.gguf
- 130,715 stars on ggml-org/llama.cpp
- 2,499 open issues and PRs
- last release v0.6.0 on 2026-10-05
- 289,279 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-10 12:58 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
aac-Q4_K_M.gguf | Q4_K_M | 104 MB |
aac-Q6_K.gguf | Q6_K | 128 MB |
aac-Q8_0.gguf | Q8_0 | 159 MB |
aac-f16.gguf | F16 | 298 MB |
From the source README
AAC Pictogram Retriever (pt-BR) — GGUF
GGUF quantizations of `Papuguinho/aac-pictogram-retriever-ptbr` for use with `llama.cpp`.
A compact Brazilian-Portuguese embedding model that finds the right ARASAAC pictogram for a short search
term — built for Augmentative and Alternative Communication (AAC). It powers pictogram search in
Papuguinho, a tool for building communication boards.
- ~157M parameters, runs comfortably on CPU (no GPU).
- One model, two jobs: *retrieval* (find the best pictogram among ~14k) and *reranking* (order a shortlist).
- ~190 MB RAM at Q8_0 — fits easily in any modern machine.
- Competitive with much larger cloud embedding APIs on this domain, while being open and self-hostable.
Model family & resources
| Resource | Description |
|---|---|
| 🧠 aac-pictogram-retriever-ptbr | Full model — sentence-transformers, retrieval + reranking, 157M, CPU |
| ⚡ aac-pictogram-retriever-ptbr-GGUF | This repo — GGUF quants for `llama.cpp` (Q4/Q6/Q8/f16) |
| 🧠 aac-board-generator-moe-636m-ptbr | MoE language model for generating board labels, 636M total / ~212M active |
| 📊 aac-pictogram-retrieval-ptbr | Evaluation benchmark (corpus / queries / qrels) |
| 🏋️ [aac-pictogram-retrieval-ptbr-training](https://huggingface.co/dataset…
Source: https://huggingface.co/Papuguinho/aac-pictogram-retriever-ptbr-GGUF
Card id model:hf:Papuguinho/aac-pictogram-retriever-ptbr-GGUF · collected 2026-10-10 12:58 UTC · JSON