Models & Labs
NVIDIA Nemotron 3 Diarization Model Released
Sam Witteveenhigh confidence
Why it matters
- →Enables local deployment of high-accuracy speaker diarization for privacy-sensitive applications.
- →Supports streaming mode, making it viable for real-time voice agent architectures.
- →Reduces dependency on third-party cloud APIs for audio processing tasks.
NVIDIA has released Nemotron 3 Diarization, a new open-weight model designed for speaker diarization in audio processing. The model supports both batch and streaming modes, enabling real-time identification of speakers in conversations. Available on Hugging Face, it allows developers to integrate speaker separation into voice AI applications locally or on edge devices like the DGX Spark. This release provides an alternative to proprietary cloud APIs for tasks requiring precise speaker attribution.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1NVIDIA Launches Nemotron 3 Ultra Model
Ollama Blog · June 4, 2026 · Related
- 2NVIDIA Unveils Nemotron 3 Ultra Model
Sam Witteveen · June 4, 2026 · Related
- 3NVIDIA Unveils Nemotron 3 Ultra for AI Agents
Matt Wolfe · June 5, 2026 · Related
- 4NVIDIA Releases Nemotron 3.5 ASR for Multilingual Streaming
Sam Witteveen · June 7, 2026 · Same story
- 5NVIDIA Nemotron 3 Ultra Boosts AI Agent Performance
NVIDIA Blog · July 8, 2026 · Related
- 6NVIDIA's Nemotron Enhances AI with Open Synthetic Data
Hugging Face Blog · July 8, 2026 · Related
- 7NVIDIA Nemotron 3.5 Lightning Launches for Local AI Agents
Ollama Blog · August 11, 2026 · Related
- 8NVIDIA Unveils Nemotron 3.5 Lightning and NeMo Switchyard
NVIDIA Blog · August 11, 2026 · Related
What happened next
- 9Nvidia releases open Nemotron models for agents and PCs
TechCrunch AI · October 19, 2026 · Related
- 10Mistral Releases Voxtral 3 Multimodal Model
Matt Wolfe · October 23, 2026 · Background
- 11llama.cpp adds LiquidAI LFM3-Audio and Omni support
llama.cpp Releases · October 28, 2026 · Background
- 12NVIDIA Nemotron powers interactive Halloween agent
Hugging Face Blog · October 30, 2026 · Related
- 13llama.cpp v0.9.0 adds FP8 and audio generation
llama.cpp Releases · November 5, 2026 · Background
More in Models & Labs
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
llama.cpp Releases
Models & Labscoding
llama.cpp b12342 adds few-row MMQ for speculative decoding
Speculative decoding just got a significant speed boost on NVIDIA GPUs. This release introduces a specialized kernel for 'few-row' matrix multiplications, targeting the small batch sizes typical of verification passes in speculative decoding workflows. By optimizing these specific operations for quantized formats like Q8_0 and IQ4 variants, llama.cpp reduces latency where it matters most during token generation. The change is CUDA-only for now but leverages hardware capabilities from Ampere onwards, making local inference faster without requiring new model architectures or complex configuration changes.
llama.cpp Releases
© TechCrunch AIModels & Labsmodels
Google deploys Gemini 4 Hydrogen for faster Search
Google is quietly shifting its search infrastructure by replacing older fast models with Gemini 4 Hydrogen, a tier designed specifically for speed and cost-efficiency rather than raw reasoning power. This model completes tasks 2.5 times faster than its predecessor while beating the more powerful Argon on specific intelligence benchmarks, proving that specialized efficiency can outperform brute force in high-volume workflows. By integrating this into Search's fan-out technique, Google now breaks down complex queries into subqueries with greater precision and speed, delivering richer visual responses without the latency of heavier models. This marks a strategic pivot toward agentic execution layers within consumer search, making AI Mode feel snappier for everyday multi-part questions.
TechCrunch AI