NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8
- Model Architecture: NemotronHForCausalLM - Input: Text - Output: Text - Model Optimizations: - Weight quantization: FP8 - Activation quantization: FP8 - Release Date: 2026-08-13 - Version: 1.0 - Model Developers: RedHatAI
Params
31.6 B
Context
262,144
Downloads 30d
357 K
Likes
2
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)357 K downloads in the last 30 days
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 | f8_e4m3 | 32.3 GB | 40.8 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 32.3 GB | 187.6 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-fp8
{
"hf_id": "RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8",
"params_b": 31.58,
"context_length": 262144,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 357352,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 40.8 }
],
"updated_at": "2026-09-18T01:00:25Z"
}
Specifications
- Architecture
- NemotronHForCausalLM
- Parameters
- 31.6 B
- Tensor type
- F8_E4M3
- Context length
- 262,144
- Vocabulary
- 131,072
- First seen on the Hub
- 2026-08-13
- Base model
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-17
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model