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.
đ baa.aiâ¡â đŹ Discord
models 78
baa-ai/ERNIE-4.5-21B-A3B-PT-RAM-12GB-MLX
Text Generation ⢠22B ⢠Updated ⢠73
baa-ai/Gemma-4-26B-A4B-it-RAM-13GB-MLX
Text Generation ⢠25B ⢠Updated ⢠702
baa-ai/Ling-mini-2.0-RAM-11GB-MLX
Text Generation ⢠16B ⢠Updated ⢠208
baa-ai/ERNIE-4.5-21B-A3B-PT-RAM-11GB-MLX
Text Generation ⢠22B ⢠Updated ⢠196
baa-ai/Qwen3.8-27B-RAM-13GB-GGUF
Text Generation ⢠27B ⢠Updated ⢠417 ⢠3
baa-ai/Qwen3.8-27B-RAM-13GB-MLX
Image-Text-to-Text ⢠27B ⢠Updated ⢠200
baa-ai/Qwen3.8-Flash-Next-RAM-91GB-MLX
Image-Text-to-Text ⢠177B ⢠Updated ⢠423 ⢠1
baa-ai/Qwen3.8-Flash-Next-RAM-91GB-GGUF
Image-Text-to-Text ⢠177B ⢠Updated ⢠797 ⢠2
baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF
Image-Text-to-Text ⢠820B ⢠Updated ⢠192
baa-ai/Krea-2-Turbo-RAM-19GB-MLX
Text-to-Image ⢠8B ⢠Updated
datasets 0
None public yet