Furiosa logo

Furiosa NXT RNGD Server

rack
8× RNGD
PCIe Gen5 x16 per card; 2 x 25G dual-port NIC for host networking
FP16
2,048
TFLOPS
FP8
4,096
TFLOPS
Power
3.0
kW Total
Memory
384
GB Total

A 4U air-cooled server holding eight Furiosa RNGD cards, and the low-power outlier of this catalogue: the whole machine draws 3 kW, which lets five of them sit in a standard 15 kW air-cooled rack where comparable GPU racks need liquid cooling. Furiosa rates it at 4,096 TFLOPS FP8, 2,048 TFLOPS FP16, 4,096 TOPS INT8 and 8,192 TOPS INT4, with 384 GB of HBM3 across the eight cards at 12 TB/s aggregate. Hosting is a dual AMD EPYC 9354 Genoa pair with 64 cores total and 1 TB of DDR5, with two 25G dual-port NICs and Ubuntu 24.04 LTS. Every figure is Furiosa's own published total and each reconciles exactly against the single RNGD card. One labelling note: this server table calls the 2,048 TFLOPS figure FP16 while Furiosa's card table calls the identical per-card rate BF16 — the chip runs both at the same speed, and each row here records the label its own document uses. Furiosa publishes rack economics alongside: five servers per rack delivering 26,400 tokens per second and serving 880 users. Furiosa labels none of its figures dense or sparse and publishes no sparse rate.

We will point you at suppliers who have it. Free, and no signup.

FP16
2,048
TFLOPS
FP8
4,096
TFLOPS
INT8
4,096
TOPS
INT4
8,192
TOPS

System Details

GPU Configuration

GPU Model: Furiosa RNGD
GPU Count: 8 GPUs
Architecture: Tensor Contraction Processor
Interconnect: PCIe Gen5 x16 per card; 2 x 25G dual-port NIC for host networking

System Specifications

Form Factor: rack
Total Power: 3.0 kW
Total Memory: 384 GB
Memory Bandwidth: 12 TB/s

Precision Performance Breakdown

PrecisionSystem PerformancePer GPUEfficiency
2,048 TFLOPS 256 TFLOPS —
4,096 TFLOPS 512 TFLOPS —
4,096 TOPS 512 TOPS —
INT4 8,192 TOPS 1,024 TOPS —

Where a vendor states a basis, the figure shown is the dense one, and any figure it publishes is listed separately. Vendors commonly headline the sparse number instead: for NVIDIA's 2:4 structured sparsity that is exactly twice the dense figure, though other vendors' sparse modes do not all follow that ratio.

Powered by Furiosa RNGD

This system utilizes 8 × Furiosa RNGD GPUs, each delivering exceptional performance for AI and HPC workloads.

Per GPU TDP

180W

Per GPU Memory

48 GB

Process Node

5nm

Architecture

Tensor Contraction Processor

Documentation & Resources

Flopper Spec Sheet

Furiosa NXT RNGD Server specifications, generated from our database. Printable.

Vendor product page

Furiosa NXT RNGD Server documentation

View ↗

FuriosaAI RNGD product page and datasheet (fai-datasheetRNGD-19-v1.1)

Furiosa • Latest version

View Document ↗

Typical Use Cases

AI/ML Training
High-Performance Computing
Data Analytics

The Furiosa NXT RNGD Server runs 8× RNGD GPUs over PCIe Gen5 x16 per card; 2 x 25G dual-port NIC for host networking, delivering 4,096 TFLOPS FP8 dense.

© 2026 Flopper.io - Compare the hardware powering AI