Prism ML · Small Language Models
Ternary Bonsai
Collection of 1.58-bit ternary-quantized Bonsai LLMs (1.7B, 4B, 8B) released in MLX 2-bit and GGUF formats, dramatically reducing memory footprint while preserving text-generation quality for on-device inference.
Open the source ↗Similar Language Models releases
- Spark-X2.6-1.7B
XHToken · On-device LLM · Week 45, 2026
- LFM3
Liquid AI · Small multimodal LFMs · Week 45, 2026
- EmbeddingGemma 2
Google DeepMind · Multimodal Embeddings · Week 42, 2026
- Claude Haiku 5.5
Anthropic · Small Frontier Model · Week 42, 2026
- Gemma Translator
Google Creative Lab · Offline Voice Translator · Week 41, 2026
- AstaBrief 8B
Allen Institute for AI (Ai2) · Open Science Report Model · Week 41, 2026
More from Prism ML
- Bonsai 27B
Prism ML · Small Language Models · Week 29, 2026
- Bonsai-8B
Prism ML · Small Language Models · Week 14, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.