Frontier model

DeepSeek V4 Pro: 1.6 trillion parameters on one node

A 1.6T MoE that reaches 27% of V3.2's per-token inference FLOPs and 10% of its KV cache at a million tokens. It got five times bigger and cheaper to run at the same time.

MIT 1.6T total 49B active 1M context

The architecture

how it is built

Hybrid CSA and HCA attention

V4 pairs two attention mechanisms rather than picking one. The combination is what gets the model to 27% of V3.2's per-token inference FLOPs and, more importantly for anyone holding the memory budget, 10% of its KV cache at 1M context.

Manifold-constrained hyper-connections

mHC replaces the plain residual stream with a constrained formulation the paper argues scales better with depth. It is also why I could not point a V3 config at it and expect anything: the serving stack needed a new tokenizer mode and new reasoning and tool-call parsers rather than reusing V3's.

A mixed-precision checkpoint

MoE expert weights are stored in FP4; attention, normalisation and router weights stay FP8. Experts are the overwhelming majority of a 1.6T model, so the checkpoint lands near 0.8 TB rather than the 1.6 TB a uniform FP8 release would cost. That single decision is the difference between a model I can host and a model I can only read about.

49B active

Three percent of the model works on any given token. The other 97% is sitting in HBM waiting to be routed to, which is exactly why total parameters decide whether you can host it and active parameters decide what it costs you.

Serving it

the playbook

An 8-GPU Blackwell node minimum, or a multi-node rack. NVIDIA's own testing on HGX B300 used MXFP4, with NVFP4 named as the planned optimisation.

On a 4,000-GPU HGX B200 fleet

500 nodes, eight B200s each, 180 GB per GPU
TP=8smallest placement that leaves a real cache budget
525 GBKV cache per replica, 40% of usable memory
1replica per HGX node
500replicas across the fleet

Weights are 800 GB (FP4 experts + FP8 attention). Usable memory is 180 GB x 0.92 per GPU, the gpu_memory_utilization from the published recipe. A placement only counts here if the cache gets at least 30% of what is left, because a config that fits the weights and nothing else cannot serve a request. Tensor parallel stays inside the NVSwitch, so no TP traffic ever crosses a NIC.

What I keep coming back to

my read

The number that stays with me is not 1.6 trillion, it is 27%. A model got five times larger and simultaneously cheaper per token than the thing it replaced, which is not how this usually goes. What I would want to know before planning capacity around it is how much of that holds up outside the vendor's own harness, because the headline throughput comes from NVL72, and on eight-GPU nodes the model fits fine but the cross-replica cache story does not transfer. Fitting is the easy half.

The numbers

measured elsewhere, not here
Total
1.6T
Active
49B
Per user
150 tok/s
Perf/watt
30x H200

Measured by NVIDIA on GB200 NVL72 against an H200 NVL8 baseline at similar interactivity. Different topology from an HGX B200 fleet.

Sources: NVIDIA Technical Blog · DeepSeek-V4 paper · Hugging Face: DeepSeek-V4-Pro