On-device
Qualcomm's Snapdragon X Elite powers the first Googlebook laptops from Dell and HP
The Dell XPS Googlebook 13 and HP Googlebook 14 use the Snapdragon X Elite and its 45 TOPS NPU to run Gemini Intelligence features, with pre-orders open.
vivo previews BlueCode phone coding agent and researches a 30B MoE on-device model
vivo showed a preview of BlueCode, a native coding agent for phones, and says it is researching a 30B-parameter BlueLM MoE model for on-device use.
OPPO unveils ColorOS 17 with an on-device linear-attention model and 128K context
OPPO says the on-device model in ColorOS 17 uses linear attention, supports 128K context and needs 48% less memory and 55% less energy than its predecessor.
Arm unveils Mali G2-Ultra NX GPU with neural accelerators in every shader core
Arm says the Mali G2-Ultra NX runs neural upscaling and frame generation on accelerators inside its shader cores, with up to 24% higher benchmark performance.
Arm unveils CSS for Mobile 2 with C2 CPU cluster, up to 1.7x faster on AI models
Arm says its C2-Ultra CPU with two SME2 units delivers up to 1.7x performance across the latest AI models and finishes an agentic workflow 24% faster.
Arm recaps Arm Create China and shows Qwen3-TTS 0.6B running on a vivo X300 CPU
Arm's Create recap shows Qwen3-TTS 0.6B on a vivo X300 CPU with SME2 at a 1.2x real-time factor and 4.7 GB peak memory.
MediaTek launches Dimensity 9600 Pro, a 2nm chip for on-device models up to 30B parameters
MediaTek says the NPU 1090 in the 2nm Dimensity 9600 Pro raises LLM prefill by 51% and supports on-device models with up to 30B parameters.
Cactus releases Needle 3, a 121M-parameter tool-calling model in an 8 to 29 MB binary
Needle 3 is a 121M-parameter model for tool calling, structured extraction and embeddings that ships as a single 8 to 29 MB binary.
ASUS announces Ascent QN10, a mini PC with Snapdragon X2 Elite and an 80 TOPS NPU
The Ascent QN10 is a mini PC under 0.7 liters with an 18-core Snapdragon X2 Elite and a Hexagon NPU rated at up to 80 TOPS for local LLM inferencing.
Edge0 releases MoE expert-offloading framework, demos 35B model on iPhone
Edge0 streams mixture-of-experts weights from storage. Its 35B tier reports 2.9 GiB peak memory on a Mac mini M4 Pro; a launch post shows a 35B model on an iPhone.
llama.cpp Hexagon NPU backend tested on a Snapdragon 8 Gen 3 phone
A user report puts Gemma 3 4B at 12.5 tokens per second of generation on a OnePlus 12 using llama.cpp’s Hexagon NPU backend, at about CPU speed but without the heat.
Qualcomm teases next-gen Hexagon NPU ahead of Snapdragon Summit 2026
Qualcomm has teased its next-generation Hexagon NPU — featuring a transformer-focused Element Accelerator and 50% more shared memory — built for on-device agentic AI ahead of the …