Diffuspace/Clover-35B-A3B-Preview
just landed · new, unvettedmodel
New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.
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; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~22.5 GB (estimated size): 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 size): 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
First published here 2026-10-24 · updated 2026-10-28 · markdown · JSON