AI Briefing#prismml
The latest AI and developer news about #prismml, with the original source and a short summary.
The latest AI and developer news about #prismml, with the original source and a short summary.
Recent commits resolve Hadamard sign tensor bottlenecks, allowing full GPU offload and fast CPU prompt ingestion for PQ2_0 models.
PrismML has released 'Ternary Bonsai 2 27B', a 27B multimodal LLM quantized to ternary values that maintains 98.2% of FP16 performance.
PrismML has released Bonsai 27B, a compressed version of the Qwen 27B model using 1-bit and ternary methods that can run even on smartphones.
PrismML unveils technology that compresses the Qwen-3.6-27B model to under 4GB to run on iPhone.
PrismML has unveiled Bonsai Image 4B, a 1-bit/ternary-based model that can run locally in the browser via WebGPU.
PrismML has released Ternary Bonsai, a family of 8B, 4B, and 1.7B LLMs using 1.58-bit ternary weights.
PrismML has developed a 1-bit compression technique that allows AI models to run on edge devices without performance degradation.