Lenovo Yoga Pro 9n runs a 120B-parameter model locally in a 1.65kg Windows laptop, with 128GB unified memory
APPSO · wechat · 2026-09-07
At IFA 2026, Lenovo unveiled the Yoga Pro 9n with NVIDIA's RTX Spark superchip (20-core Grace CPU fused with a 6,144-CUDA-core Blackwell GPU via NVLink-C2C), delivering 1 PFLOP (FP4) in a 1.65kg chassis with up to 128GB unified memory — the first mass-produced Windows laptop able to run a 120B-parameter model with 1M-token context locally.
Unified memory breaks the VRAM bottleneck, echoing Apple's playbook (M5 Ultra Mac Studio at 512GB; 4-unit Thunderbolt clusters running trillion-parameter models). The significance is bringing this into the Windows+CUDA ecosystem, challenging Mac and Linux dominance of local LLM workstations.
Lenovo also showed the ThinkCentre X Ultra (a 1.6L DGX Spark rival with 128GB unified memory, clusterable up to four units), dropped Qira's requirements to 16GB-RAM PCs, and previewed rollable-screen and fanless solid-state-cooling concepts. The AI PC metric is shifting from feature count to how much cloud work can stay on your machine.
More from Infra
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27
- Celesto launches CI runners nearly 90% cheaper than GitHub Actions, with agent sandboxes — aniketmaurya · 2026-10-27
- Supabase founders on rebuilding the backend for a billion AI-built apps — Latent Space · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- Site tracks US city council topics: data centers rank only behind pickleball courts — zakkohane · 2026-10-27