nvidia / text-generation updated 2 months ago

Nemotron-Labs-Diffusion-8B

Name: Nemotron-Labs-Diffusion-8B
Author: nvidia

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...

Params

8.5 B

Context

262,144

Downloads 30d

206 K

Likes

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

206 K176 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	17.1 GB	20.6 GB	⚠️ Tight — reduce context
model.safetensors (bf16, full)	bf16 + 256K ctx	17.1 GB	60.1 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/nemotron-labs-diffusion-8b
{
  "hf_id": "nvidia/Nemotron-Labs-Diffusion-8B",
  "params_b": 8.49,
  "context_length": 262144,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 206435,
  "vram_estimates": [
    { "quant": "bf16", "gb": 20.6 }
  ],
  "updated_at": "2026-07-28T18:08:42Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: NemotronLabsDiffusionModel
Parameters: 8.5 B
Tensor type: BF16
Context length: 262,144
Vocabulary: 131,072
Layers / heads: 34 / 32
Licence: other
First seen on the Hub: 2026-03-18
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB