Model Intelligence Sheet
baa-ai/paddock-reader-35b-gguf overview
Paddock Reader 35B GGUF Optional big reader for the baa.ai Paddock console auto router escalation / high quality mode . 35B A3B MoE, RAM optimized quantization…
Runs locally from ~14.11 GB disk (16 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 |
|---|---|---|---|---|
| Qwen3.5-35B-A3B-RAM14.gguf | GGUF | GGUF | 14.11 GB | Download |
Model Details
Model README
---
license: apache-2.0
tags: [gguf, paddock, baa-ai]
---
Paddock Reader 35B (GGUF)
Optional big reader for the baa.ai Paddock console (auto-router escalation / high-quality
mode). 35B-A3B MoE, RAM-optimized quantization, GGUF. ~15.2 GB; recommend >=24 GB RAM or GPU.
Enable at install with PADDOCK_BIG_READER=1 or pull later; verify against SHA256SUMS.
Run baa-ai/paddock-reader-35b-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models