# Zen 6 Max — Hanzo AI

> One model name. 3.7 trillion parameters across a routed fusion: Enso picks the specialist for each request, with a long context, tools and code.

# Zen 6 Max

3.7 trillion parameters across a routed fusion. Each request runs on the specialist Enso picks, so it behaves as one model.

[Talk to sales](https://hanzo.ai/contact-sales)[Run it on your own GPUs](https://hanzo.ai/enterprise)

### One name

You call Zen 6 Max. You never choose among the models behind it.

### The right specialist, per request

Enso reads each request and runs it on the specialist built for that kind of work, transparently.

### Long context

A long context, for large codebases and long documents.

### Tools and code

Tool calls and code, built in.

Enterprise deployment

## On your own premises

What a rack for Zen 6 Max is made of.

We recommend at least four 8-GPU NVIDIA Blackwell servers, B300 or B200, for Zen 6 Max on your own premises. Routing cuts the average inference work a request needs. It does not cut the memory needed to keep every specialist ready.

## DGX B300

GPUs8 x B300

GPU memory8 x 288 GB, 2,304 GB

Cluster network8 x 800 Gb/s InfiniBand or Ethernet

Data cache8 x 3.84 TB

[NVIDIA DGX B300 user guide: 8 x 288 GB GPU memory](https://docs.nvidia.com/dgx/dgxb300-user-guide/introduction-to-dgxb300.html)

## DGX B200

GPUs8 x B200

GPU memory1,440 GB

Cluster network8 x ConnectX-7, up to 400 Gb/s

Data cache8 x 3.84 TB

[NVIDIA DGX B200 user guide: 1,440 GB total GPU memory](https://docs.nvidia.com/dgx/dgxb200-user-guide/introduction-to-dgxb200.html)

Four B300 servers hold 9,216 GB of GPU memory; four B200 servers hold 5,760 GB.

### Planning range

Qualification. Four 8-GPU servers is where a qualification starts.

Isolated production pools. One pool for each specialist, so a busy class of work never takes memory from another.

Redundant pools. Two independent replicas of those pools across failure domains.

### Around the servers

NVLink and NVSwitch inside each server.

400 or 800 Gb/s RDMA wherever a specialist spans servers.

About 31 TB of NVMe in each server (8 x 3.84 TB).

Separate sandbox workers for coding agents.

A high-availability control cluster.

Final capacity and performance commitments come from qualifying your workload: context length, concurrency, routing mix, latency, and failover.

[Talk to sales](https://hanzo.ai/contact-sales)