NVIDIA Blackwell
NVL72 rack-scale coherent GPU domains, the default substrate for frontier training and inference.
Full NVIDIA Blackwell record →Head to head
NVIDIA Blackwell vs SambaNova SN40L
NVIDIA Blackwell (NVIDIA) and SambaNova SN40L (SambaNova) both sit in Chips & Compute. NVIDIA Blackwell shipped more tracked changes in the last 30 days (9 vs 6). Every value below comes from the latest crawl of the vendors' own pages.
| Attribute | NVIDIA Blackwell NVIDIA | SambaNova SN40L SambaNova |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | GB200 NVL72 | SN40L |
| Entry cost | Pricing not publicly available (enterprise hardware/rack scale) | Free tier available, followed by Pay-as-you-go developer tier. |
| Pricing tiers | — | Free free · Developer Pay as you go free |
| Model stack | Blackwell · Blackwell B200 · Grace CPU | DeepSeek-V3.1 · gpt-oss-120b · Llama / DeepSeek open weights · Llama 3.1 · Llama 3.1 (8B, 70B, 405B) · Llama 3.1 405B · Llama 3.1 70B · Llama 3.1 8B · MiniMax M2.7 · RDU dataflow · SambaRack SN40-16 · SN40L RDU |
| Context window | — | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 9 | 6 |
| Origin | Global | Global |
| Capabilities | 72-GPU NVLink domain, FP4 inference, HBM3E 192GB, CUDA ecosystem, Second-generation Transformer Engine, Fifth-generation NVLink, FP4 AI Support, Tensor Cores with microscaling formats | three-tier memory, many models per node, fast open-model serving, Reconfigurable Dataflow Unit (RDU), Three-tier memory architecture, Dataflow processing, Low power inference, Multi-model concurrency |
SambaNova SN40L
Reconfigurable dataflow units with three-tier memory for serving many models per node.
Full SambaNova SN40L record →