NVIDIA-Nemotron-Nano-9B-v2-FP8
NVIDIA-Nemotron-Nano-9B-v2-FP8 is a quantized version of NVIDIA-Nemotron-Nano-9B-v2 and is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt....
Params
8.9 B
Context
131,072
Downloads 30d
190 K
Likes
15
Download history
daily snapshots · 96 days
▲ 16 K in the last 30 days (7.8%)
205 K145 K
Oct 12Oct 22Nov 1Nov 10
209 K145 K
Aug 13Sep 12Oct 12Nov 10
209 K145 K
Aug 7Sep 8Oct 10Nov 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 | f8_e4m3 | 10.3 GB | 13.1 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 10.3 GB | 33.1 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 -s https://aimodelscomparison.com/api/v1/models/nvidia-nemotron-nano-9b-v2-fp8
{
"hf_id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8",
"params_b": 8.89,
"context_length": 131072,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 189956,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 13.1 }
],
"updated_at": "2026-08-07T01:00:36Z"
}
Specifications
- Architecture
- NemotronHForCausalLM
- Parameters
- 8.9 B
- Tensor type
- F8_E4M3
- Context length
- 131,072
- Vocabulary
- 131,072
- Layers / heads
- 56 / 40
- Licence
- other
- First seen on the Hub
- 2025-09-22
- Base model
- NVIDIA-Nemotron-Nano-9B-v2
- Training datasets
- nvidia/Nemotron-Post-Training-Dataset-v1, nvidia/Nemotron-Post-Training-Dataset-v2, nvidia/Nemotron-Pretraining-Dataset-sample, nvidia/Nemotron-CC-v2, nvidia/Nemotron-CC-Math-v1, nvidia/Nemotron-Pretraining-SFT-v1
- Added to our catalog
- 2026-08-07
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model