# lean-agent-cruiser - leanmodels.ai

*Cruiserweight class, v1.0, DeepSeek V4-Flash base*

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

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
- **Tool calling:** not yet supported
- **Tier:** Paid
- **License:** MIT

## Source weights

The exact public GGUF this model is packed from, pinned to a commit. Download it and you can reproduce our numbers with stock llama.cpp.

- **Repository:** [unsloth/DeepSeek-V4-Flash-GGUF](https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF/tree/e3aa0d6a5fa4f820d9e132ac1fd1d01e1b2b49e0)
- **Revision:** `e3aa0d6a5fa4f820d9e132ac1fd1d01e1b2b49e0`
- **Quantization:** UD-Q4_K_XL
- **Source size:** 155.10 GB (5 files)
- **This .lmpack:** 155.14 GB - core mostly Q8_0, experts mostly MXFP4

Packing splits the source GGUF into an offloadable layout, so the .lmpack size differs from the source file. K-quantized weights are mixed by design - the dtypes named are the ones holding the most bytes, not the only ones present.

## Not yet verified

This model hasn't been benchmarked or verified on our hardware yet. Performance and hardware requirements are targets, not measured results; download sizes are measured wherever the model is already packed. No download or purchase until it clears the same verification the available models passed.

## Get the model

- **Download:** 155.14 GB (single .lmpack, from UD-Q4_K_XL)