recipes.vllm.ai
recipes.vllm.ai is DeepSeek's first experimental multimodal V4 model — the V4-Flash MoE backbone plus a 32-layer vision tower, 1M context, and a fused DSpark draft module.. It is ranked #101 on the Dev Radar, in Hosting & infra, first seen 18 days ago and shared in 11 posts (141k views).
What people said about recipes.vllm.ai on X
🐳 DeepSeek-V4.1-Flash is out, and vLLM serves it from day 0, verified on NVIDIA and AMD GPUs! 🎉 552B MoE backbone, native vision, 1M context. Built for agents: 8B active while it reads your prompt, 16B while it writes. If you already run DeepSeek-V4 on vLLM, most of this stack will feel familiar: the…
— @vllm_project, 9 days ago · 478 likes · see the post
🎉 Congrats to @deepseek_ai on DeepSeek-V4-Flash-Vision-Exp, the first multimodal model in the V4 family! vLLM serves it now. A vision encoder and aligner on the 285B/13B V4-Flash MoE backbone, with text-agent scores holding steady. 🚀 🔗 https://recipes.vllm.ai/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
— @vllm_project, 18 days ago · 252 likes · see the post
🚀 Day-0 support for @intern_lm Intern-S2-397B is now available in vLLM! Built for long-horizon scientific research, Intern-S2 brings strong multimodal, reasoning, coding, and scientific agent capabilities. Run it with vLLM today 👇 🔗 https://recipes.vllm.ai/internlm/Intern-S2-397B
— @vllm_project, 5 days ago · 135 likes · see the post
Alternatives to recipes.vllm.ai
- boat by ASCII — ascii box is now boat ( )
- Railway — Bring context from your work and personal accounts into the same conversation. Connect your accounts in the plugin…
- Nebius Token Factory — Start building
- click.alibabacloud.com — Model Studio
- serverkit — ServerKit is a lightweight, modern server control panel for managing web applications, databases, and services on your…
- Qwen-Omni — Qwen-Omni,Alibaba Cloud Model Studio:Use Qwen-Omni over HTTP to understand text, images, audio, and video. Choose…
recipes.vllm.ai in numbers
- Rank on the Dev Radar: #101 of 1228
- Shared in 11 posts by 7 accounts: @vllm_project, @woosuk_k, @simon_mo_, @OpenBMB
- 141k views on those posts
- First seen 18 days ago, last shared 5 days ago
- Pricing seen by Jev: not stated
- Market: Hosting & infra
FAQ
What is recipes.vllm.ai?
DeepSeek's first experimental multimodal V4 model — the V4-Flash MoE backbone plus a 32-layer vision tower, 1M context, and a fused DSpark draft module. It was first shared on X 18 days ago and is ranked #101 on the Dev Radar.
Is recipes.vllm.ai free?
Pricing is not stated on the page we read.
Who shared recipes.vllm.ai?
7 accounts on X, including @vllm_project, @woosuk_k, @simon_mo_, in 11 posts totalling 141k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 11.3k posts from 4.9k X accounts over the last 21 days, 1.2k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 16:50 UTC. Full method.