NVIDIA's Qwen3.5-4B draft model for Qwen3.8-27B trends on Hugging Face
nvidia · hf · 2026-11-19
nvidia/Qwen3.5-4B-Qwen3.8-27B-Draft is trending on Hugging Face under text-generation, built with NVIDIA Model Optimizer (ModelOpt) and released in safetensors format. The naming indicates a 4B draft model built to accelerate Qwen3.8-27B inference via speculative decoding — and hints at the existence of the Qwen3.5/3.8 family.
Related event: NVIDIA Releases Draft Model to Accelerate Speculative Decoding(2 posts)→
More from Infra
- Google open-sources TPU codesign guide: 8 principles for LLM/MoE performance — rseroter · 2026-11-19
- vLLM team's Inferact to build an autonomous inference system around vLLM — vllm_project · 2026-11-19
- AI Stocks Plummet as Burry's Bubble Call Lands: CoreWeave -74%, Oracle -65% — SumitGup · 2026-11-19
- Banks offload $800M of AI data center debt, including loans tied to Oracle's Stargate — SumitGup · 2026-11-19
- BIS interim rule targets cloud remote access to US chips; CNAS unpacks what it gets right and wrong — paul_scharre · 2026-11-19
- Japanese neocloud Datasection slashes revenue guidance 89%, stock limit-down — dylan522p · 2026-11-19