RedHatAI / text-generation updated 3 days ago

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
Licence: unknown Not gated SAFETENSORS View on Hugging Face ↗

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.

FileQuantSizeEst. VRAMVerdict 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 · api/v1
$ 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"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

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