China Hot Tech @ChinaHotTech
← All posts
Edge AI · Robotics · GPU

Iluvatar TY1200: Offline Robot Physics Sim on a Desk-Side Edge Box

天数智芯 (Iluvatar CoreX) showed its 彤央 TY1200 edge compute terminal at a Shanghai media open day 「从模型到世界」 around Nov 2, 2026 — a desk-side box that, in the vendor demo*, ran MuJoCo-Warp GPU physics simulation offline and finished policy training plus walk/stand validation on a 3D-printed MicroDuck robot duck*. This is the edge SKU story; it is distinct from the Nov 2 morning Tiangai 300 cloud GPU post already on this site. Iluvatar listed in Hong Kong in January 2026*.

· ~8 min read · China Hot Tech

Editorial desk-side edge compute box with cool teal-amber glow — Iluvatar TY1200 robotics terminal vibe

Illustration: desk-side edge-box / robotics-lab palette — distinct from today’s Zhizi optical and Lingchuan video-chip posts, and from the Nov 2 Tiangai 300 cloud-GPU story.

Robot learning still defaults to “train in the cloud, pray the sim transfers.” Nvidia’s GTC Microduck demos leaned on cloud GPUs; Iluvatar’s claim at the Shanghai open day is the opposite pitch: an early domestic edge product that can keep MuJoCo-Warp physics and policy loops on the desk*. If that holds beyond a staged demo, the interesting change is not another TOPS slide — it is whether a China edge box can close the sim→policy→action loop without shipping every frame to a cluster. For labs that already live inside Chinese OEM supply chains, that is a deployability question; for everyone else, it is a signal about where edge GPU software stacks are being forced to mature.

TY1200 — dense TOPS, not sparse peak*

TY1200 is rated at 300 TOPS dense (稠密) compute* — the company stresses dense, not sparse peak marketing*. That framing matters for anyone comparing China edge SKUs to Jetson / Thor class parts: sparse peaks inflate charts; dense rating is closer to what sustained physics and LLM decode actually feel like. The Tongyang (彤央) line is described as 「1 ecosystem + 2 form factors + 5 SKUs」* — modules for R&D plus plug-and-play terminals*. TY1000 already shows up in a robot-dog face-follow local demo*; TY2000 is previewed as next-gen ~600T dense*.

Can you buy it?

TY1200 is a China edge / OEM terminal story — not Digi-Key, not a Western retail board, not an AWS/GCP instance. Access path today is partner deployments and Iluvatar’s Tongyang stack inside China*; overseas engineers should treat benches and demos as vendor claims* until a channel SKU and third-party measurements appear.

Editorial still of an edge robotics compute terminal with teal-amber highlights — TY1200 MuJoCo/MicroDuck vibe

Editorial still in the same desk-lab palette. LLM/VLM/Cosmos ratios and deployment numbers below are vendor / press figures*.

Vendor benches vs Nvidia Thor T5000*

Iluvatar published head-to-heads against Nvidia Thor T5000*. Treat every ratio as first-party*. On LLMs: Qwen3.8-27B / Qwen3.6-35B-A3B ~1.2× overall*; Qwen3.8-27B-AWQ generation throughput 1.38×*; Qwen3.6-35B-A3B-AWQ 1.10×*. On VLMs: Qwen2.5-VL-3B-Instruct 1.80×* (BS32 1.18×*). Cosmos-R2-2B at 158%* and Cosmos-R2-8B at 180%* of Thor T5000*. A live same-prompt demo cited TTFT 0.223 s vs Thor 0.411 s* and 30.21 tok/s vs 24.46 tok/s*. Vendor attribution: higher memory bandwidth + more compute cores*. Separately, a MiniMax open video model ran locally in ~6 minutes for a 1056×608 / 5 s clip* — useful as a local-gen latency anecdote, not a standardized bench.

Software story and 「算力分层」*

Product messaging is 「算力分层 / compute layering」 plus 「端云同源」: train in cloud, deploy on edge, re-judge in cloud*. Tongyang PM 宋远盈 Song Yuanying* walks that loop. Software stack branding is 「用AI开发AI」: FlyDSL + an agentic kernel path*; claims include PD deploy <10 min* and optimize cycles from 7 days → 2 hours*. Those are vendor productivity claims* — asterisk hard; no independent audit here.

Deployments cited*

Press lists verticals*: Hohai University JinTan battery lab vertical agent producing reports in ~2 minutes*; Shanghai Sunshine Rehab companion robot for the visually impaired*; museum day-guide / night CV train*; emergency CV + multimodal smoke detection accuracy from 70% → 95%* (vendor). TY1200 also took a 2026 CIIF 工博会国芯展创新成果奖*. Design-wins and award plaques are real marketing signals; they are not substitute for open benches or export SKUs.

What changes — and what does not

For overseas robotics / edge engineers, the watch item is whether MuJoCo-Warp-class physics and mid-size Qwen/Cosmos workloads stay local on a China-made desk box with usable software (FlyDSL / agentic kernel), not whether another 300 TOPS sticker appears. The Tongyang framing — modules for R&D plus plug-and-play terminals* — is trying to sell a product line, not a single open-day demo. Contrast stays important: Tiangai 300 is the cloud/datacenter GPU narrative; TY1200 is the edge terminal that claims to close robot sim+train on-prem*. Today’s Zhizi optical seed and Lingchuan SL200 video-SoC posts sit in different layers of the stack.

Bottom line: Iluvatar is pitching Tongyang TY1200 as a desk-side edge box that can keep physics sim and mid-size multimodal workloads offline — MicroDuck walk/stand as the showpiece*, dense 300 TOPS* and Thor-relative benches* as the spreadsheet. Asterisk the ratios and the deployment percentages; watch whether FlyDSL and partner terminals make the loop reproducible outside a media open day.

Sources