The post names the model size, active parameters, and throughput on a single GB200, showing how a 40B MoE can be served on one GPU with vLLM.
Day-0 support for @Recursive_SI's Flint is here in vLLM! 🚀
40B parameters, just 2.5B active per token. Thanks to the small size, our custom NVFP4 kernels push it to 500 TPS on a single GB200, even at 100K context without speculative decoding.
Both NVFP4 and BF16 are ready to run today! https://vllm.ai/blog/2026-10-21-flint
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. • Best-in-class fast local coding • Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark • Built from scratch in under 4 months Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
vLLM · x.comPublished · added here
Original title: Day-0 support for @Recursive_SI's Flint is here in vLLM! 🚀
