NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
--- libraryname: transformers license: other licensename: openmdw-1.1 licenselink: https://openmdw.ai/license/1-1/ pipelinetag: text-generation language: - en - es - fr - de - it - ja tags: - nvidia - pytorch - nemotron-3.5 trackdownloads: true ---
Params
17.8 B
Context
1,048,576
Downloads 30d
1.0 M
Likes
493
Download history
daily snapshots · 86 days
▲ 186 K in the last 30 days (22.5%)
1.1 M829 K
Oct 12Oct 22Nov 1Nov 10
1.3 M196 K
Aug 17Sep 14Oct 13Nov 10
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 | u8 | 21.6 GB | 26.9 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 1024K ctx | 21.6 GB | 366.4 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 -s https://aimodelscomparison.com/api/v1/models/nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4
{
"hf_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4",
"params_b": 17.82,
"context_length": 1048576,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 1011751,
"vram_estimates": [
{ "quant": "u8", "gb": 26.9 }
],
"updated_at": "2026-09-11T01:00:11Z"
}
Specifications
- Architecture
- NemotronHForCausalLM
- Parameters
- 17.8 B
- Tensor type
- U8
- Context length
- 1,048,576
- Vocabulary
- 131,072
- Layers / heads
- 52 / 32
- Licence
- other
- First seen on the Hub
- 2026-08-04
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-17
Compare with any text-generation model