Gradium launches compact on-device TTS model Phonon with no network requirement
The 65–75 MB model covers five languages, tops German and Spanish intelligibility, and leads CPU streaming speed benchmarks
AI news and practical stories on this subject.
The 65–75 MB model covers five languages, tops German and Spanish intelligibility, and leads CPU streaming speed benchmarks
Foundry Local runs Qwen3.8-27B locally on NVIDIA GPUs with 24 GB VRAM, connects to GitHub Copilot, and works offline.
FP8 tensors on MPS: 5–6.5× MoE decoding speedups; Wan2.2 video VAE memory drops from ~270 GiB to 8 GiB; softmax ~8× faster; complex64 LU factorization added.
NVIDIA and Microsoft announce RTX Spark laptop availability for Friday, Oct. 16. Nemotron 3.5 Bolt 74B model releases Oct 15 for agentic AI. Adobe claims up to 2x faster AI in creative apps.
Microsoft says GitHub Copilot will choose on-device or cloud models per task by end of October 2026. Local performance figures are vendor-reported.
RTX Spark laptops are open for preorder, available from October 16. NVIDIA's claims about local model use without cloud data are vendor statements, not independent tests.
The 740M-parameter model maps text, code, images, audio, and video into a shared embedding space. Weights are on Hugging Face and Kaggle; Model Garden availability is coming soon.
Load a GGUF model from the Hub by passing its ID and filename to from_pretrained. Packed inference is MPS-only for now and supports Qwen3.5 and compatible Qwen3.8 architectures.
NVIDIA Personal AI Router enables users to cluster local compute resources to speed up multi-agent AI workflows without infrastructure overhauls.