LesenForschungRadarAnlageframework
Anmelden / Registrieren
← Zurück zur Lektüre
NewsThema · Clover-35BWesentlich1 Min. LesezeitDisconfirmAI Redaktion

Shenzhen's DiffuSpace Open-Sources Clover-35B Model, Claims Lead Over Autoregressive Peers in Agent Benchmarks

DiffuSpace has released and open-sourced Clover-35B, a MoE diffusion language model. Vendor tests show it outperforms same-size autoregressive models like Qwen3.6 in SWE-bench and other agent tasks.

2026-10-28 19:35 GMT+8

On October 28, 2026, Shenzhen-based AI firm DiffuSpace announced the release and open-sourcing of its latest diffusion language model, Clover-35B-A3B-Preview. The model utilizes a Mixture-of-Experts (MoE) architecture with 35 billion total parameters and 3 billion active parameters, supporting a thinking mode.

According to benchmark results published by the company, Clover-35B-A3B-Preview ranked first among same-level models in six agentic coding and tool-use tasks, including SWE-bench Verified and Terminal-Bench2.1. Its performance reportedly exceeds that of other diffusion models like LLaDA2.2 flash and same-sized autoregressive models such as Qwen3.6-35B-A3B. Specifically, it achieved a score of 73.6 on SWE-bench Verified.

In terms of inference efficiency, internal tests showed the model reaching a generation speed of 680 tokens/s on a single NVIDIA GB300 GPU at BF16 precision. Across 49 agent tasks, the median execution time was reported as 1.52 seconds. Additionally, DiffuSpace previewed a decision-making model for structured judgment tasks, claiming a 95.0% accuracy rate for its 'joint mode' in internal validation.

All performance metrics are self-reported by the vendor and have not yet been independently reproduced. The model weights are available on Hugging Face and GitHub.

Quellen

Anmelden / Registrieren
LesenForschungRadarAnlageframework
zhidx.com
↗
Thema

Clover-35B

深圳扩散智能(DiffuSpace)于2026年10月28日发布并开源了首个扩散语言模型Clover-35B-A3B-Preview。该模型基于阿里Qwen3.6-35B-A3B初始化,采用混合专家架构(MoE),总参数350亿、激活参数3…

4 Schritte1 BeiträgeAktualisiert 2026-10-29 17:04

Wie es dazu kam

  1. 2022-01-01核心团队启动dLLM前沿研究,提出DiffuSeq,开创扩散模型处理序列到序列文本生成的技术路径。zhidx.com ↗
  2. 2025-04-01港大NLP实验室推出扩散语言模型Dream 7B,证明小尺寸扩散模型可与自回归模型竞争。diffuspace.ai ↗
  3. 2026-10-09扩散智能首次公布融资,连续完成两轮融资,总金额数亿元人民币,创下全球dLLM最大规模融资纪录。zhidx.com ↗

Was noch ungeklärt ist

  • Clover-35B-A3B-Preview的Agent能力提升有多少来自扩散解码机制,多少来自针对Qwen3.6基座的额外后训练?
  • 何时会发布官方支持的GGUF量化版本或合并SGLang PR,以降低本地部署门槛?
  • 是否有第三方机构对官方公布的SWE-bench 73.6分及680 tokens/s速度进行独立复测验证?
Vollständiges Thema lesen →
Recherche fortsetzen →