NVIDIA
Llama 3.1 Nemotron Instruct 70B
Open weights
- Intelligence
- 6.9
- Rank 578 of 744 measured models
- Output speed
- 33.9 t/s
- Rank 381 of 403 measured models
- Price/1M
- $1.20
- Rank 404 of 659 measured models
- Context window
- 128K
- Rank 773 of 1199 measured models
Llama 3.1 Nemotron Instruct 70B scores 6.9 on the Artificial Analysis Intelligence Index, ranking 578th of 744 measured models. The closest models on this index are Grok Beta (6.9), Llama 3.1 Instruct 8B (6.9), and Qwen2.5 Instruct 32B (6.9). At $1.20 per million tokens (3:1 input/output blended price), it is more expensive than Llama 3.1 Instruct 8B ($0.043). With an output speed of 33.9 t/s, it is slower than Llama 3.1 Instruct 8B (139 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Command A+
Cohere · $4.38 · 61.5 t/s
7.0+0.1$4.3861.5 t/sCompare - Grok Beta
SpaceXSI · — · —
6.9——Compare - Llama 3.1 Instruct 8B
Meta · $0.043 · 139 t/s
6.9$0.043139 t/sCompare - Qwen2.5 Instruct 32B
Alibaba · — · —
6.9——Compare
