DiffuSpace releases Clover-35B-A3B-Preview, an open diffusion language model it says beats Qwen3.6-35B-A3B
READ THE ORIGINAL SOURCEOpen original sourcehuggingface.co · Opens in a new tabDiffuSpace releases Clover-35B-A3B-Preview, a Mixture-of-Experts diffusion language model with 35B total and 3B activated parameters, under an Apache license. The company says it outperforms the similarly sized autoregressive model Qwen3.6-35B-A3B across multiple benchmarks while generating significantly faster. It reports 73.6 on SWE-bench Verified, 51.7 on Terminal-Bench 2.1, and 680 tokens/s on internal agent workloads on a single GB300 GPU.
⚑ Review needed · why this is flagged
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
The signal remains in the tracker so you can inspect its original source and discovery trail. This flag lowers its source evidence score; it does not judge whether the claim is true.
One primary source; other links are context, not independent corroboration.
- Primary sourcePrimary source discovery · source check open
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Review needed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
DiffuSpace releases Clover-35B-A3B-Preview, a Mixture-of-Experts diffusion language model with 35B total and 3B activated parameters, under an Apache license. The company says it outperforms the similarly sized autoregressive model Qwen3.6-35B-A3B across multiple benchmarks while generating significantly faster. It reports 73.6 on SWE-bench Verified, 51.7 on Terminal-Bench 2.1, and 680 tokens/s on internal agent workloads on a single GB300 GPU.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: huggingface.co. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Clover-35B-A3B-Preview reports 73.6 on SWE-bench Verified and 51.7 on Terminal-Bench 2.1.
- The model reports 680 tokens/s on internal agent workloads on a single NVIDIA GB300 GPU with BF16.
- Weights and code are released under Apache license on Hugging Face and GitHub, with SGLang and llama.cpp support.
- It reports 101.8 tokens/s on MATH-500 when deployed with INT4 quantization on an RTX 5070 Ti with 16GB VRAM.
Source claims not independently checked; benchmark comparisons and speed figures come from the developer's own internal tests and settings.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
DiffuSpace's Clover-35B-A3B-Preview is a 35B MoE diffusion language model with 3B active parameters, derived from Qwen3.6-35B-A3B under Apache-2.0. DiffuSpace reports 73.6 on SWE-bench Verified and says it beats Qwen3.6-35B-A3B while generating faster. Blog dated Oct 30; these are the developer's own numbers.
Source claims not independently checked; benchmark comparisons and speed figures come from the developer's own internal tests and settings.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
If the reported results hold, open diffusion language models could offer a competitive speed-quality tradeoff against autoregressive models for agentic and on-device workloads, an area where generation latency compounds across steps.
Limits and open questions
Source claims not independently checked; benchmark comparisons and speed figures come from the developer's own internal tests and settings.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.