Model Intelligence Sheet
baa-ai/paddock-reader-9b-gguf overview
Paddock Reader 9B GGUF Default grounded answering reader for the baa.ai Paddock console. 9B parameters, 8/4 bit mixed quantization, GGUF llama.cpp — Metal, CUD…
Runs locally from ~6.82 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| baa-ai-3.5-9B-8-4.gguf | GGUF | GGUF | 6.82 GB | Download |
Model Details
Model README
---
license: apache-2.0
tags: [gguf, paddock, baa-ai]
---
Paddock Reader 9B (GGUF)
Default grounded-answering reader for the baa.ai Paddock console. 9B parameters, 8/4-bit
mixed quantization, GGUF (llama.cpp — Metal, CUDA, or CPU). ~6.8 GB; recommend >=16 GB RAM (CPU)
or any >=8 GB GPU. Context: run with n_ctx 4096-8192. Downloaded automatically by the Paddock
installer and container; verify against SHA256SUMS.
Run baa-ai/paddock-reader-9b-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models