Models & Labs
PrismML Tiny LLM Runs on Qualcomm Smart Glasses
TechCrunch AIhigh confidence
Why it matters
- →Demonstrates viable local inference for multimodal tasks on wearable hardware.
- →Challenges the necessity of cloud-based processing for real-time AI applications.
- →Highlights Qualcomm's expanding role in enabling specialized edge AI ecosystems.
AI Lab PrismML demonstrated its Bonsai LLM running locally on Qualcomm’s Snapdragon AR1 Gen 1 platform during the Snapdragon Summit. The startup, founded by Caltech researchers, optimized a 2-billion-parameter model to operate efficiently on smart glasses hardware. This deployment allows for real-time vision and language processing directly on the device, bypassing cloud dependencies. Although no commercial smart glasses utilizing this specific model have been announced, the demo highlights a shift toward open-weight, edge-native AI solutions.
Read originalMore from TechCrunch AI
© TechCrunch AIMarket & Regulationbusiness
Crusoe cancels $1.25B Boom turbine deal
The collapse of Crusoe’s $1.25 billion order for Boom Supersonic’s stationary turbines exposes the fragility of AI infrastructure financing. While Crusoe raised $3.9 billion, it pivoted away from on-site gas generation, opting instead for grid power and diverse energy mixes. This signals that even well-funded data center operators are prioritizing flexibility over massive, long-term capital commitments to specialized hardware. Boom’s pivot to sell jet engines as power plants was a bold bet on AI energy needs, but losing its anchor customer suggests the market is more cautious than anticipated.
TechCrunch AI
© TechCrunch AIMore in Models & Labs
Models & Labsother
llama.cpp b11193 adds Snapdragon Hexagon and ROCm 10
This release quietly expands llama.cpp's hardware support to include Qualcomm's Hexagon NPU on Linux arm64, a significant step for local inference on Snapdragon devices. It also updates CUDA builds to version 13.4 and introduces ROCm 10.0 binaries, keeping the project aligned with the latest NVIDIA and AMD driver ecosystems. KleidiAI on Apple Silicon is temporarily disabled in this build, likely due to stability checks rather than a feature rollback. For developers targeting edge AI or diverse GPU stacks, this update ensures broader compatibility without requiring custom compilation.
llama.cpp Releases
© Lev SelectorModels & Labsmodels
NVIDIA NVFP4 and SoL-Pi Token Efficiency
NVIDIA introduced the NVFP4 4-bit format and SoL-Pi technology, which uses 2x fewer tokens for improved efficiency.
