Llama 3.1 Nemotron Instruct 70B
Llama 3.1 Nemotron Instruct 70B is a text-based AI model by NVIDIA. It features 32 tok/s output speed, $1.20/1M input tokens pricing. It scores 13.4 on the intelligence index.
Weaknesses
- -Slower than average output (32 tok/s)
Benchmarks
Intelligence13.4Coding10.8Math11.0
MMLU-Pro
0.7
GPQA
0.5
LiveCodeBench
0.2
Intelligence
13.4
Coding
10.8
Math
11.0
Output Speed
32 tok/s
Latency (TTFT)
0.35s
Blended Price
$1.20/M
Pricing per 1M Tokens
| Input (Prompt) | $1.20 |
| Output (Completion) | $1.20 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare Llama 3.1 Nemotron Instruct 70B with:
Alternatives to Llama 3.1 Nemotron Instruct 70B
More from NVIDIA
Frequently Asked Questions
How much does Llama 3.1 Nemotron Instruct 70B cost?
Llama 3.1 Nemotron Instruct 70B costs $1.20/1M input tokens and $1.20/1M output tokens.
Is Llama 3.1 Nemotron Instruct 70B good for coding?
Llama 3.1 Nemotron Instruct 70B has a lower coding score of 10.8. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is Llama 3.1 Nemotron Instruct 70B?
Llama 3.1 Nemotron Instruct 70B generates output at 32 tok/s. Time to first token is 0.35s.
Is there a free version of Llama 3.1 Nemotron Instruct 70B?
No, Llama 3.1 Nemotron Instruct 70B is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to Llama 3.1 Nemotron Instruct 70B?
Last updated: