---
title: Diffuspace/Clover-35B-A3B-Preview
url: https://recentmodel.com/models/Diffuspace/Clover-35B-A3B-Preview/
status: just landed · new, unvetted
published: 2026-10-24T03:46:30Z
updated: 2026-10-28T11:20:27Z
source: https://huggingface.co/Diffuspace/Clover-35B-A3B-Preview
---

# Diffuspace/Clover-35B-A3B-Preview

Clover-35B-A3B-Preview is the first model released by DiffuSpace, delivering performance among open-source diffusion language models at release on the benchmarks reported in our launch blog. Mixture-of-experts, 35B total, 3B active (256 experts, 8 per token). Context: 128K tokens (config). License: apache-2.0. Vendor-reported: "Clover-35B-A3B-Preview is the first model released by DiffuSpace, delivering state-of-the-art performance among open-source diffusion language models at release on the benchmarks reported in our launch blog." Vendor-reported: "Clover is a text-only model derived from Qwen3.6-35B-A3B, retaining its hybrid Gated DeltaNet (GDN) / full-attention MoE backbone with 40 layers, 256 routed experts, top-8 token routing, and one shared expert per layer."

- Vendor-reported: Clover-35B-A3B-Preview is the first model released by DiffuSpace, delivering state-of-the-art performance among open-source diffusion language models at release on the benchmarks reported in our launch blog.
- Vendor-reported: Clover is a text-only model derived from Qwen3.6-35B-A3B, retaining its hybrid Gated DeltaNet (GDN) / full-attention MoE backbone with 40 layers, 256 routed experts, top-8 token routing, and one shared expert per layer.

- **Org:** Diffuspace
- **Released:** 2026-10-24
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 34.7B total, 3.0B active
- **Architecture:** MoE · 256 experts, 8/token · CloverMoeModelLM
- **Context:** 131,072 tokens
- **Task:** text-generation · text
- **Signal:** 45 HF likes · 105 downloads

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~22.5 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~38.5 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~71.0 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/Diffuspace/Clover-35B-A3B-Preview)