# lean-reason-heavy - leanmodels.ai

*Heavyweight class, v1.0, Qwen 3.5 base*

Near-frontier - deep reasoning, complex analysis, research

397B total, 17B active per token. Near-frontier reasoning from a massive expert pool, running entirely on your hardware.

## Specifications

- **Total params:** 397B
- **Active per token:** 17B
- **Base model:** Qwen3.5-397B-A17B
- **Architecture:** GDN hybrid MoE
- **Experts:** 256 experts, 8 active
- **Target VRAM / RAM:** 48 GB / 64 GB
- **Tool calling:** supported on non-streaming requests; streaming does not emit tool_call deltas yet
- **Tier:** Paid
- **License:** Apache 2.0

## 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/Qwen3.5-397B-A17B-GGUF](https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF/tree/da33c16fa4440f831149fcf53b98a22bc07785e5)
- **Revision:** `da33c16fa4440f831149fcf53b98a22bc07785e5`
- **Quantization:** UD-Q4_K_XL
- **Source size:** 245.27 GB (6 files)
- **This .lmpack:** 226.17 GB - core mostly Q6_K, experts mostly Q4_K

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