| meta-llama/llama-3.1-8b-instruct-bf16 | meta | — | |
| CodeLLaMa 7B Instruct Solidity | meta | — | |
| Llama 3 Lumimaid 70B | meta | — | |
| Llama 3 Lumimaid 8B | meta | — | |
| Lumimaid v0.2 70B | meta | — | |
| Lumimaid v0.2 8B | meta | — | |
| Llama 3.1 Nemotron 70B Instruct | meta | — | |
| Llama 3.1 Nemotron Ultra 253B v1 | meta | — | |
| Llama 3.1 Sonar 70B Online | meta | — | |
| Llama 3.1 Sonar 8B Online | meta | — | |
| Llama 3.3 Nemotron Super 49B v1 | meta | — | |
| Typhoon2 70B Instruct | meta | — | |
| meta-llama/llama-2-13b-chat | meta | — | |
| meta-llama/llama-2-70b-chat | meta | 4,096 | - Input
- Input (cache write)
- Input (cached read)
- Output
|
| meta-llama/llama-3.1-405b | meta | 8,000 | |
| meta-llama/llama-guard-2-8b | meta | 8,192 | |
| Llama Guard 3 8B | meta | 131,072 | |
| codellama/CodeLlama-13b-Instruct-hf | meta | — | |
| codellama/CodeLlama-34b-Instruct-hf | meta | — | |
| codellama/CodeLlama-70b-Instruct-hf | meta | — | |
| codellama/CodeLlama-7b-Instruct-hf | meta | — | |
| meta-llama/Llama-2-13b-chat-hf | meta | — | |
| meta-llama/Llama-2-70b-chat-hf | meta | — | |
| meta-llama/Llama-2-7b-chat-hf | meta | — | |
| meta-llama/Llama-3-70b-chat-hf | meta | — | |