Updated daily at 05:00 UTC
Language
Llama Nemotron
NVIDIA post-trained and pruned derivatives of Meta Llama, with a reasoning on/off switch from 2025.
By NVIDIA.
Versions
9 versions
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| Llama 3.3 Nemotron Super 49B v1.5Llama Nemotron · Open weights | NVIDIA | Language | 25 Jul 2025 | 131.1K | — | — |
| Llama 3.1 Nemotron Nano VL 8B v1Llama Nemotron · Legacy · Open weights | NVIDIA | Language | 3 Jun 2025 | — | — | — |
| Llama 3.1 Nemotron Nano 4B v1.1Llama Nemotron · Legacy · Open weights | NVIDIA | Language | 3 May 2025 | 131.1K | — | — |
| Llama 3.1 Nemotron Ultra 253B v1Llama Nemotron · Legacy · Open weights | NVIDIA | Language | 7 Apr 2025 | 131.1K | — | — |
| Llama 3.1 Nemotron Nano 8B v1Llama Nemotron · Legacy · Open weights | NVIDIA | Language | Mar 2025 | 131.1K | — | — |
| Llama 3.3 Nemotron Super 49B v1Llama Nemotron · Legacy · Open weights | NVIDIA | Language | Mar 2025 | 131.1K | — | — |
| Mistral-NeMo-Minitron 8B InstructLlama Nemotron · Legacy · Open weights | NVIDIA | Language | 2 Oct 2024 | 8.2K | — | — |
| Llama-3.1-Nemotron-70B-InstructLlama Nemotron · Legacy · Open weights | NVIDIA | Language | Oct 2024 | 131.1K | — | — |
| Llama-3.1-Nemotron-51B-InstructLlama Nemotron · Legacy · Open weights | NVIDIA | Language | Sep 2024 | 131.1K | — | — |
- Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 25 Jul 2025 · 131.1K context—in / 1M
- Llama 3.1 Nemotron Nano VL 8B v1NVIDIA · 3 Jun 2025 · — context—in / 1M
- Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 3 May 2025 · 131.1K context—in / 1M
- Llama 3.1 Nemotron Ultra 253B v1NVIDIA · 7 Apr 2025 · 131.1K context—in / 1M
- Llama 3.1 Nemotron Nano 8B v1NVIDIA · Mar 2025 · 131.1K context—in / 1M
- Llama 3.3 Nemotron Super 49B v1NVIDIA · Mar 2025 · 131.1K context—in / 1M
- Mistral-NeMo-Minitron 8B InstructNVIDIA · 2 Oct 2024 · 8.2K context—in / 1M
- Llama-3.1-Nemotron-70B-InstructNVIDIA · Oct 2024 · 131.1K context—in / 1M
- Llama-3.1-Nemotron-51B-InstructNVIDIA · Sep 2024 · 131.1K context—in / 1M