NVIDIA RTX PRO 6000 Blackwell Server Edition
VRAM
96 GB
Memory
GDDR7 ECC
Bandwidth
1,597 GB/s
FP16
1,000 TF
TDP
600 W
Memory and compute
Architecture and power
Notes
Passive dual-slot server variant. FP4 4 PF / FP8 2 PF / FP16 1 PF dense per NVIDIA datasheet. Popular single-card inference option in 1U/2U racks.
Models that may fit on NVIDIA RTX PRO 6000 Blackwell Server Edition
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
More GPUs by NVIDIA
The manufacturer's other cards in the catalog, largest memory first, with bandwidth and power where published.
Frequently asked questions about NVIDIA RTX PRO 6000 Blackwell Server Edition
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
NVIDIA RTX PRO 6000 Blackwell Server Edition has 96 GB of GDDR7 ECC at 1,597 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 76B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Llama 3.1 Nemotron 70B Instruct HF, Gemma 4 31B IT, Llama Nemotron Embed VL 1B V2 and GLM Z1 9B 0414 fit on a single NVIDIA RTX PRO 6000 Blackwell Server Edition with their default context. The list on this page shows the estimated memory each takes; the capacity planner sizes any model against this card for your own context length, batch size and request rate.
1,597 GB/s. Bandwidth bounds how fast a model generates tokens, because every token reads the whole set of weights and the KV cache from memory; at this rate a 76B model at INT8 could be read on the order of 21 times a second on one card, before batching and framework efficiency.
NVIDIA RTX PRO 6000 Blackwell Server Edition has a TDP of 600 W, in the PCIe form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
NVIDIA RTX PRO 6000 Blackwell Server Edition is a datacenter accelerator, meant for servers and multi-GPU serving, built on the Blackwell architecture and released in 2025. It has no multi-GPU interconnect, so a model must fit on one card or be split over the slower PCIe bus.
Specifications from the manufacturer's published material; a figure that is not published is shown as such, and a derived one is explained in the notes.
Added Jul 30, 2026 · Last updated Jul 30, 2026
Explore more
Companion tools that draw on the same catalog and routing engine.
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.