NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF
> [!IMPORTANT] > This model is automatically converted using https://github.com/ggml-org/convert
Params
—
Context
—
Downloads 30d
269 K
Likes
32
Download history
daily snapshots · 22 days305 K191 K
Aug 31Sep 7Sep 14Sep 21
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 |
|---|---|---|---|---|
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_0.gguf | Q4_0 | 18.9 GB | 21.3 GB | ⚠️ Tight — reduce context |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q8_0.gguf | Q8_0 | 33.6 GB | 37.4 GB | ❌ Won’t fit |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16.gguf | GGUF | 63.2 GB | 70.0 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$ ollama run nvidia-nemotron-3-5-lightning-30b-a3b-gguf # pin the quantization explicitly $ ollama run nvidia-nemotron-3-5-lightning-30b-a3b-gguf-q4_0
$ huggingface-cli download ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF-GGUF \
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_0.gguf --local-dir .
$ llama-cli -m NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/nvidia-nemotron-3-5-lightning-30b-a3b-gguf
{
"hf_id": "ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 268634,
"vram_estimates": [
{ "quant": "GGUF", "gb": 70.0 },
{ "quant": "Q4_0", "gb": 21.3 }
],
"updated_at": "2026-09-13T04:00:21Z"
}
Specifications
- Licence
- other
- First seen on the Hub
- 2026-08-11
- Base model
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-31
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model