Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Hugging Face Unveils DiffusionGemma: A Diffusion LLM That Generates 1,500 Tokens per Second

AI By Crimson AI Hugging Face Papers 4 August 2026 · 00:00 18 views
Share: X Telegram

DiffusionGemma, an experimental open-weight model from Hugging Face, uses discrete diffusion to generate text in parallel blocks of 256 tokens, achieving around 1,500 output tokens per second on a single H100 GPU—far outpacing autoregressive models.

Hugging Face Unveils DiffusionGemma: A Diffusion LLM That Generates 1,500 Tokens per Second

Key points

Hugging Face has released a technical report introducing DiffusionGemma, an experimental open-weight language model that leverages discrete diffusion to generate text at exceptional speeds. Instead of decoding one token at a time like conventional autoregressive (AR) models, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, effectively bypassing the sequential decoding bottleneck.

The model is built by fine-tuning the mixture-of-experts Gemma 4 model, which has 3.8 billion activated parameters and 25.2 billion total parameters. This compute-efficient approach uses less than 10% of the original AR model's total training token budget, achieved through a two-stage pipeline: first, supervised fine-tuning to teach bidirectional denoising, and second, a combination of reinforcement learning and sampler distillation to jointly improve generation quality and inference efficiency.

According to the report, DiffusionGemma establishes a new Pareto frontier for the trade-off between generation speed and model capability. On average, it generates around 20 tokens per forward pass and achieves roughly 1,500 output tokens per second on a single NVIDIA H100 GPU—substantially faster than AR models even with state-of-the-art speculative decoding.

Despite the diffusion fine-tuning, DiffusionGemma retains support for thinking mode, multimodal inputs, and long contexts. It also remains capable of AR generation with only minor performance degradation, suggesting a promising path toward hybrid diffusion-AR decoding in future models.

MetricValue
Activated parameters3.8B
Total parameters25.2B
Tokens per forward pass~20
Output tokens per second (H100)~1,500
Training token budget vs. AR model<10%
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1