← All models

lean-reason-heavy

Heavyweight class · v1.0 · Qwen 3.5 base

Near-frontier - deep reasoning, complex analysis, research

Coming soonPaid

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

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) ~244.1 GB - single .lmpack, Q4_K_M