Diffuspace/Clover-35B-A3B-Preview
text-generation model by Diffuspace
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
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. Clover combines a 35B-parameter mixture-of-experts backbone with approximately 3B active parameters per token, block diffusion generation, and a 128K context window. Blog · Code & inference backends · Hugging Face [](https://diffuspace.ai/blog/clover-35b/#agentic-benchmarks) See the benchmark discussion for evaluation results, settings, and comparisons. 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. For self-speculative decoding with our SGLang and llama.cpp implementations, see the official code repository. Install PyTorch with CUDA support, then the Hugging Face dependencies. The example below uses Transformers 5.19.0 and PyTorch 2.10 or later. Use a GPU with enough memory for the BF16 weights (approximately 69 GB) plus inference…
Read the full model card ↗ · Preview checked 2026-10-29T09:47:55.554Z
Inside the original model card — Document outline
- Clover-35B-A3B-Preview
- Performance
- Architecture and decoding
- Quick start
- Generation controls
- Expert selection
- Serving and evaluation
- Upstream attribution and modifications
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Diffuspace/Clover-35B-A3B-Preview is a text-generation model repository published by Diffuspace on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 2,021
- Cumulative likes
- 193
- Hugging Face trending score
- 189
- Reported safetensors parameters
- 34,661,350,848
- Architecture
- CloverMoeModelLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-24T03:46:30.000Z
- Last modified
- 2026-10-28T03:07:54.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.6-35B-A3B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:49:30.141Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.