Tenstorrent logo vs

Tenstorrent Wormhole n150s vs NVIDIA GeForce RTX 4090 24GB

The GeForce RTX 4090 delivers 26% more FP8 throughput than the Wormhole (330 vs 262 TFLOPS dense). The GeForce RTX 4090 also carries 12 GB more memory (24 GB vs 12 GB).

Wormhole: Wormhole, 2024 GeForce RTX 4090: Ada Lovelace, 2022
FP8 dense lead
+26%
GeForce RTX 4090: 330 vs 262 TFLOPS
VRAM
12 vs 24 GB
12 GB more for the GeForce RTX 4090
Bandwidth
288 GB/s vs 1.0 TB/s
GeForce RTX 4090 moves data faster
TDP
160 W vs 450 W
Wormhole draws 290 W less

Specifications

Tenstorrent logo
Wormhole
GeForce RTX 4090
Architecture
WormholeAda Lovelace
Launch Year
20242022
Form Factor
PCIePCIe
VRAM
12 GB24 GB
Memory Bandwidth
288 GB/s1.0 TB/s
TDP
160 W450 W
Process Node
4nm

Performance (TFLOPS)

Tenstorrent logo
Wormhole
GeForce RTX 4090
FP64
No verified data available1.3 TFlops
FP32
No verified data available82.6 TFlops
TF32
No verified data available82.6 TFlops
sparse not published
BF16
No verified data available165.2 TFlops
sparse not published
FP16
74.0 TFlops 165.2 TFlops
sparse not published
FP8
262.0 TFlops 330.3 TFlops
sparse not published
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
No verified data available660.6 TFlops
1321.2 TOPS sparse

FLOPS by Precision

What actually differs

The Wormhole is the newer part: Wormhole, launched in 2024, against the GeForce RTX 4090's Ada Lovelace from 2022. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the Wormhole against the GeForce RTX 4090: FP16 74 vs 165 TFLOPS, FP8 262 vs 330 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 12 GB against 24 GB, fed at 288 GB/s versus 1.0 TB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.

Frequently asked questions

Is the Wormhole faster than the GeForce RTX 4090?

At FP8 precision the GeForce RTX 4090 reaches 330 TFLOPS dense against 262 TFLOPS for the Wormhole. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the Wormhole or the GeForce RTX 4090?

The GeForce RTX 4090 carries 24 GB of VRAM versus 12 GB for the Wormhole. Memory bandwidth is 288 GB/s for the Wormhole and 1.0 TB/s for the GeForce RTX 4090.

How much power do the Wormhole and the GeForce RTX 4090 draw?

The Wormhole is rated at 160 W TDP and the GeForce RTX 4090 at 450 W. On FP32 throughput per watt, the GeForce RTX 4090 is the more efficient part.

Can I rent the Wormhole or the GeForce RTX 4090 in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.27 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA GeForce RTX 4090 24GB

ProviderConfigurationPrice/GPU-hrChecked
Vast.ai
2× GeForce RTX 4090 24GB Community $0.27 1h ago View →
RunPod
1× GeForce RTX 4090 24GB Community $0.34 1h ago View →
Excess Supply
8× GeForce RTX 4090 24GB $0.40 1h ago View →
RunPod
1× GeForce RTX 4090 24GB $0.74 1h ago View →
All GeForce RTX 4090 listings and price history →

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.