← All models

lean-agent-cruiser

Cruiserweight class · v1.0 · DeepSeek V4-Flash base

Million-token context - frontier long-context work on a single GPU

MITComing soonPaid

284B total, 13B active per token. DeepSeek's hybrid attention pairs Compressed Sparse Attention with Heavily Compressed Attention to hold a 1,048,576-token context, and Manifold-Constrained Hyper-Connections stabilise signal propagation across its 43 layers.

Specifications

Total params

284B

Active per token

13B

Base model

DeepSeek-V4-Flash

Architecture

Hybrid CSA/HCA attention MoE

Experts

256 experts, 6 active + 1 shared

Target VRAM / RAM

24 GB / 64 GB

Not yet verified

This model hasn't been benchmarked or verified on our hardware yet. Sizes and specs are targets, not measured results. It won't be available for download or purchase until it clears the same verification the available models passed.

Get the model

Download (target) ~155.1 GB - single .lmpack, UD-Q4_K_XL