PrismML
PulseAugur coverage of PrismML — every cluster mentioning PrismML across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
Bonsai-Ternary-27B model runs complex AI tasks locally on 16GB GPU
A user shared their experience running the Bonsai-Ternary-27B model locally on a 4060Ti 16GB GPU for knowledge base management and productivity tasks. The model successfully handled complex tasks, including querying, sy…
-
Apple Inc. eyes PrismML for larger on-device iPhone AI models
Apple Inc. is reportedly considering integrating PrismML's technology to enhance its on-device AI capabilities for iPhones. This move could enable the company to deploy larger AI models, such as a 27-billion-parameter m…
-
Apple in talks with PrismML to enable on-device AI for iPhone
Apple Inc. is reportedly in discussions with PrismML, a startup specializing in AI model compression. The goal of these talks is to enable sophisticated AI models to run directly on devices like the iPhone. This collabo…
-
Bonsai 27B model runs on phones; Google's Gemma 4 optimized for Pixel 10
PrismML has released Bonsai 27B, a 27-billion parameter model that can run on smartphones by utilizing 1-bit and ternary weights, reducing its size to under 6GB. This model supports complex tasks like multi-step reasoni…
-
PrismML releases Bonsai 27B, enabling Qwen3.6-27B on laptops and phones
PrismML has released Bonsai 27B, a highly compressed version of Qwen3.6-27B, available in 1-bit and ternary variants. These models are designed to run on consumer hardware like laptops and phones, with the 1-bit version…
-
PrismML compresses 27B AI model to fit on smartphones
PrismML has developed Bonsai 27B, a 27-billion-parameter multimodal AI model that has been compressed to approximately 3.9 GB, making it capable of running on mobile phones. This significant compression, achieved throug…
-
Apple in talks with PrismML to shrink AI models
Apple Inc. is reportedly in discussions with PrismML, a company specializing in AI model optimization. The potential collaboration aims to develop methods for shrinking large AI models, which could enable more efficient…
-
PrismML's Bonsai 27B model runs on iPhone, efficiency gains noted
PrismML has released Bonsai 27B, a 27-billion parameter AI model capable of running on a mobile device like the iPhone 17 Pro using only 3.9 GB of memory. A 1-bit variant of this model has been highlighted for its effic…
-
Bonsai 27B: 1-bit LLM runs in browser, shrinks to 3.8GB
The PrismML team has released Bonsai 27B, a 1-bit quantized large language model that can run locally in a web browser. This quantization technique reduces the model's size from 54GB to 3.8GB, while reportedly maintaini…
-
Startup shrinks 27B parameter AI model to run on iPhone
PrismML, a startup backed by Khosla, has developed a method to significantly compress large AI models, enabling them to run on mobile devices like the iPhone. Their compressed version of Alibaba's Qwen 3.6 model, with 2…
-
Apple explores 1-bit AI architecture for iPhone 17 Pro
Apple Inc. is reportedly exploring the integration of 1-bit architecture technology from PrismML. This potential integration could enable the iPhone 17 Pro to perform advanced AI tasks locally, significantly reducing en…
-
Apple explores PrismML tech for on-device AI on iPhones
Apple Inc. is reportedly in discussions with PrismML, a startup specializing in shrinking large AI models for on-device functionality. The goal is to enable iPhones to run more powerful AI models without relying on exte…
-
OpenAI agent usage surges; open-source models shrink for local inference · 4 sources tracked
OpenAI's agent products, including Codex and ChatGPT Work, have seen a significant surge in usage, with demand for GPT-5.6 Sol described as "insane" and potentially causing scaling issues. In response, JetBrains has rec…
-
PrismML releases tiny Bonsai Image 4B models for local devices
PrismML has released Bonsai Image 4B, a pair of diffusion transformer models designed for efficient image generation on local devices. The 1-bit Bonsai Image 4B utilizes binary weights, while the Ternary Bonsai Image 4B…
-
PrismML releases Bonsai Image for local AI art generation on iPhone
PrismML has released Bonsai Image, a new open-source image generation model that can run locally on iPhones. This model is capable of generating images in as little as 12 seconds, offering users a way to create AI art w…
-
Ollama v0.30.0, Qwen3.5 35B, and 1-bit AI on WebGPU
Ollama's v0.30.0 pre-release is set to improve llama.cpp interoperability. Separately, a new Qwen3.5 35B model is available in GGUF and GPTQ formats, optimized for local inference on consumer GPUs. Additionally, PrismML…
-
PrismML releases compact 1-bit/ternary image diffusion models
PrismML has released new text-to-image diffusion transformer models, Binary and Ternary Bonsai Image 4B. These models are significantly smaller than previous versions, with a size of approximately 3GB, and can run local…