Nemotron-Labs-Diffusion

About

What Nemotron-Labs-Diffusion is

Nemotron-Labs-Diffusion-8B [](./assets/demo.mp4) Model Overview Nemotron-Labs-Diffusion is a tri-mode language model that supports both AR decoding and diffusion-based parallel decoding by simply switching the attention pattern of the same model during inference. The synergy between these two modes enables a third mode, called self-speculation: the same model performs diffusion-based parallel drafting and AR verification with shared KV cache, achieving high acceptance lengths and decoding efficiency. The seamless mode switching by simply changing attention patterns enables high efficiency at different concurrency levels in varying deployment scenarios with one single model. Highlights - SOTA 3B, 8B, 14B dense LM family (base, instruct, and vision-language variants) supporting AR, diffusion, and self-speculation with the focus on decode efficiency. - Generation moved from a memory-bound regime toward a compute-bound regime. Model weights are loaded once and reused to compute multiple tokens during generation. - Self-speculation uses diffusion for drafting and AR for verification, providing a stronger alternative to MTP approaches: 3x higher acceptance length and 2.2x speed-up vs. Qwen3-8B-Eagle3 in SGLang. 5.9× tokens per forward over Qwen3-8B (no MTP) with the same accuracy. - Real-device speed-up across platforms: DGX Spark (8B, concurrency 1): 2.7x faster with 112 tok/sec vs. 41.8 tok/sec AR using w4a16. GB200 (8B, concurrency 1): 3.3x faster with 850 tok/sec vs. 253 tok/sec AR and 360 tok/sec Eagle3. Custom CUDA kernels boost to 1015 tok/sec (4x). - Diffusion speedup-of-light analysis shows that throughput can be further doubled (vs. current best) for a single user with better sampling - future research. License/Terms of Use Use of this model is governed by the NVIDIA Nemotron Open Model License. Environment Chat with Our Model Inference with Linear Self-Speculation + LoRA-enhanced Drafter An optional LoRA adatper can be applied to the diffusion drafter in the linear self-speculation mode to further increase the acceptance length: Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys nemotron-labs-diffusion for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nemotron-labs-diffusion below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nemotron-labs-diffusion","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Commercial licence needed

Sources

Weights & code

Explore

More language models