One model for both halves of RAG retrieval; a strong default per size. Contact baa.ai for the optimal pick for your corpus.
AI & ML interests
Model Quantization
Recent Activity
View all activity
Organization Card
Black Sheep AI.
Smaller. Smarter. Sovereign.
Making frontier models run anywhere
We publish high-quality quantized models for Apple Silicon and GGUF. Our models use a proprietary optimisation method that delivers superior quality at your target memory budget.
Browse our models, or connect with us below.
models 80
baa-ai/Kolibri-1-RAM-50GB-MLX
Text Generation • 78B • Updated • 343
baa-ai/Qwen3.8-27B-RAM-13GB-GGUF
Text Generation • 27B • Updated • 598 • 3
baa-ai/Qwen3.8-27B-RAM-24GB-MLX
Image-Text-to-Text • 27B • Updated • 536 • 3
baa-ai/Krea-2-Turbo-RAM-19GB-MLX
Text-to-Image • 8B • Updated
baa-ai/Krea-2-Turbo-RAM-8bit-MLX
Text-to-Image • 4B • Updated
baa-ai/Krea-2-Turbo-RAM-9GB-MLX
Text-to-Image • 3B • Updated
baa-ai/Qwen3.8-27B-RAM-31GB-GGUF
Text Generation • 27B • Updated • 43
baa-ai/paddock-reader-35b-gguf
35B • Updated • 64 • 1
baa-ai/paddock-reader-9b-gguf
9B • Updated • 63
baa-ai/GLM-5.2-RAM-333GB-MLX
563B • Updated • 92
datasets 0
None public yet