On-device
Liquid AI releases LFM2.5-24B-A2B, a 2B-active MoE for local agents
Liquid AI reports 184 tok/s on an Apple M5 Max for its 24B-parameter mixture-of-experts model, which activates 2.45B parameters per token.
Qualcomm CEO says AI companies want 100B-parameter models running on phones by 2028
Cristiano Amon says unnamed AI companies have asked Qualcomm for phones that can run at least a 100-billion-parameter model almost continuously by 2028.
FunctionGemma 270M fine-tune reaches 76.5% on 15 mobile actions, with an Android demo
Fine-tuning FunctionGemma 270M on 9,500 synthetic mobile-action conversations raises end-to-end accuracy from 29.3% to 76.5%, with a Pixel 8 Pro demo app.
Google adds local model support to the Antigravity SDK with Gemma 4 on LiteRT
Antigravity agents can now run on Gemma 4 26B A4B through LiteRT, with Google recommending more than 24 GB of VRAM or unified memory.
Nvidia releases Nemotron-3-Diarization, a 100M speaker model with 0.32 second latency
Nemotron-3-Diarization labels up to eight speakers in streaming or offline audio and ranks first on Voice Arena’s Diarization-Bench v1 with 14.7% DER.
Perplexity brings its local Portable Computer agent to AMD Ryzen AI Max PCs
Portable Computer runs Qwen 3.8 27B or PPLX 27B locally on Windows PCs with AMD Ryzen AI Max chips and at least 24 GB of GPU-accessible memory.
Liquid AI releases a DSpark drafter that speeds up LFM2.5-VL-3B decoding
Liquid AI’s 280M-parameter draft model speeds up decoding of its 3B vision-language model by up to 3.13x on Apple Silicon, for 8.9% more parameters.
Qualcomm positions Snapdragon X2 as an agentic PC chip and previews Linux support
Qualcomm says its Snapdragon X2 platform now delivers up to 85 TOPS and up to twice the tokens per second of the first-generation X Elite for on-device AI agents.
Hugging Face adds native GGUF inference to Transformers, starting with Qwen3.5 on Macs
Transformers now loads GGUF models in packed form and runs them on Apple Silicon GPUs via Metal kernels, starting with Qwen3.5.
Apple launches M6 Mac mini and M5 Ultra Mac Studio for local AI
Apple’s new Mac Studio scales to 512GB of unified memory, which Apple says lets researchers run large language models entirely on device.
MediaTek launches Dimensity CX C10 Max, a 55 TOPS chip for Googlebook
MediaTek’s Dimensity CX C10 Max is a 3nm chip with a 55 TOPS NPU built for Google’s new Googlebook laptop category.
Qualcomm launches Snapdragon 8 Elite Extreme Gen 6 for 30B-parameter AI
Qualcomm’s Snapdragon 8 Elite Extreme Gen 6 gives its Hexagon NPU 50% more shared memory to run 30B-parameter MoE models on a phone.