Google releases DiffusionGemma 26B, open-weight model generates 500+ tokens/second
Google has released DiffusionGemma 26B, an open-weight text generation model under Apache 2 license. The model generates over 500 tokens/second according to testing on NVIDIA's free NIM API, where it produced 2,409 tokens in 4.4 seconds.
How DiffusionGemma ranks now
| Benchmark | Score | Rank | Source |
|---|---|---|---|
| GPQA | 73.2% | 134 of 163 | llm-stats, Jul 2026 ↗ |
| MMLU-Pro | 77.6% | 51 of 75 | llm-stats, Jul 2026 ↗ |
| AIME 2026 | 69.1% | 24 of 26 | llm-stats, Jul 2026 ↗ |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.
Google releases DiffusionGemma 26B, open-weight model generates 500+ tokens/second
Google has released DiffusionGemma 26B, an open-weight text generation model licensed under Apache 2. The model is based on Google's previously experimental Gemini Diffusion architecture from May 2025, which briefly appeared in preview before being withdrawn.
Performance metrics
The model demonstrates generation speeds exceeding 500 tokens per second. In testing on NVIDIA's NIM cloud API, DiffusionGemma 26B generated 2,409 tokens in 4.4 seconds when creating an image description. This represents a significant speed improvement over standard autoregressive language models.
Google's earlier Gemini Diffusion preview in May 2025 reportedly achieved 857 tokens per second, suggesting the architecture maintains high-speed generation capabilities.
Availability and access
The model is available as google/diffusiongemma-26B-A4B-it on Hugging Face. NVIDIA is currently hosting the model free of charge on their NIM cloud API platform, providing immediate access without local deployment requirements.
The 26B parameter model uses a diffusion-based approach to text generation rather than traditional autoregressive decoding, which enables parallel token generation and faster inference speeds.
Technical details
DiffusionGemma represents a departure from standard transformer architectures that generate tokens sequentially. Instead, the diffusion approach allows multiple tokens to be refined simultaneously during generation, similar to image diffusion models adapted for discrete text.
The "A4B" designation in the model name likely indicates architecture-specific configuration details, though Google has not released full technical specifications.
What this means
DiffusionGemma 26B validates diffusion architectures as a viable alternative to autoregressive generation for language models. The 500+ tokens/second speed, combined with Apache 2 licensing, makes this the fastest openly available language model by generation speed. This could shift inference economics for applications requiring high-throughput text generation, though quality comparisons with standard models like Llama or Gemma remain to be established through independent benchmarking.
Related Articles
KiteFishAI releases NanoI1, a 155-million-parameter open-weight model for local enterprise use
KiteFishAI has released NanoI1, an open-weight model with 155 million parameters. It targets specialized enterprise workflows on local hardware, according to Unite.AI.
Tencent releases Hy4 Flash Base: 220B-parameter MoE, 12B active, 1M-token context
Tencent has published Hy4 Flash Base on Hugging Face: a 220B-parameter mixture-of-experts model with 12B active parameters per token, text and image input, and a 1M-token context. Tencent calls it its most cost-effective Hy model to date.
Apple releases FastFrames-L, a 14B two-step video model distilled from Wan2.1-14B for interactive 480p generation
Apple has released FastFrames-L (14B) and FastFrames-S (1.3B), autoregressive two-step video diffusion models that generate 480p video at interactive latency. FastFrames-L is distilled from Wan2.1-14B, and the repository lists 35.4 ms total latency for FastFrames-S on one GPU.
OpenAI's GPT-6.2 Astra ranks second on Artificial Analysis index at 62, behind Claude Fable 5.2 (65)
OpenAI released GPT-6.2 Astra and GPT-6.2 Sol. Artificial Analysis ranks Astra second in its Intelligence Index with 62 points, behind Claude Fable 5.2 at 65, and finds coding performance flat versus the previous generation. Astra's API price is $8 per 1M input tokens and $40 per 1M output tokens.
Comments
Loading...