Meta MTIA 400 vs Meta MTIA 450
The MTIA 450 delivers 17% more FP8 throughput than the MTIA 400 (7,000 vs 6,000 TFLOPS dense).
Meta MTIA 400
Full specs →Meta MTIA 450
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
The MTIA 450 is the newer part: MTIA, launched in 2027, against the MTIA 400's MTIA from 2026. 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 MTIA 400 against the MTIA 450: FP8 6,000 vs 7,000 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 288 GB against 288 GB, fed at 9.2 TB/s versus 18.4 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 MTIA 400 faster than the MTIA 450?
At FP8 precision the MTIA 450 reaches 7,000 TFLOPS dense against 6,000 TFLOPS for the MTIA 400. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the MTIA 400 or the MTIA 450?
Both GPUs carry 288 GB of memory. Memory bandwidth is 9.2 TB/s for the MTIA 400 and 18.4 TB/s for the MTIA 450.
How much power do the MTIA 400 and the MTIA 450 draw?
The MTIA 400 is rated at 1.2 kW TDP and the MTIA 450 at 1.4 kW.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.