NVIDIA shows speculative decoding speeding up LLM inference on Jetson with Qwen3.5 9B
NVIDIA Developer · youtube · 2026-10-27
NVIDIA Developer published a video and companion blog posts explaining how speculative decoding accelerates on-device LLM inference on Jetson:
- Mechanism: a draft model proposes multiple tokens at once, verified in parallel by the target model, cutting sequential generation steps
- Demoed with Qwen3.5 9B NVFP4, comparing generation with speculative decoding on vs off
- Results depend on model, hardware, and workload
- Includes two tech blogs (intro to speculative decoding; deploying frontier reasoning models on Jetson) plus Jetson AI Lab resources
More from Infra
- Anthropic S-1 reveals $800B+ in off-books future compute commitments — GaryMarcus · 2026-10-27
- ~42% of Anthropic's ~11GW contracted compute is NVIDIA GPUs — ns123abc · 2026-10-27
- EdgeRock-4B holds KV cache at 72 MiB across 256K context, 99.1% smaller than Qwen3.5-4B — alifcoder · 2026-10-27
- RTX 5080 price jumps from $1658 to $2318 in ten days on Amazon — Frizzy-MacDrizzle · 2026-10-27
- ComfyUI on 12GB VRAM: measured peaks show offloading turns 24s into 11 minutes — Impossible-Mail-4619 · 2026-10-27
- Neon rebuilds its docs search entirely on its own stack: Lakebase Search, Functions, AI Gateway — matei_zaharia · 2026-10-27