Blog

Moondream has been acquired by Prime Intellect. Together, we will accelerate open models and fast multimodal AI.

Photon runs Qwen3.5-27B at over 400 tokens per second on one B200. FP8 and DFlash speculative verification are now part of our megakernel compiler.

Up to 70% lower speech startup latency than vLLM-Omni. Qwen3-TTS and Kokoro are now available in Photon.

Meet Moondream Parakeet Redux and Parakeet Ultra: speech-to-text models for local transcription in 25 languages, on CPUs and GPUs.

Photon 2.2 adds five NVIDIA GPUs, Ampere to Blackwell. Parakeet runs 3.1x to 4.8x NeMo's throughput. Qwen3-ASR beats vLLM in 23 of 24 benchmarked configurations.

Photon 2.1 adds automatic speech recognition for Whisper, Qwen3-ASR, and Parakeet, beating each model's reference engine in every matched test, and brings the full model catalog to NVIDIA B200.

A 13× throughput collapse, minute-long cold boots, memory that never comes back: why datacenter inference engines break on live video, with receipts.

Photon compiles models into GPU programs optimized for the chip and the job. The first release supports Moondream, Qwen, and Gemma on NVIDIA H100, and wins every matched throughput test against vLLM and SGLang.

Moondream 3.1 launches with best-in-class benchmark scores, a new fine-tuning motion that transfers to your tasks, and a partnership with Cloudflare.