Meta
Meta
Llama-3.3-70B-Instruct
Model
Meta
Meta
Llama-3.3-70B-Instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

372 Versions
trtllmapi-pt-runtime-params-a100-sxm4-40gbx8-throughput-bf16-uoswlqfxbqSelectedSigned
02/04/2026 7:08 PM UTC1.61 KB
trtllmapi-pt-runtime-params-h200x2-latency-fp8-3ur-jvqwswSigned
01/26/2026 6:58 PM UTC1.54 KB
trtllmapi-pt-runtime-params-rtx6000-blackwell-svx4-latency-bf16-teblpznxhqSigned
01/14/2026 11:54 PM UTC1.82 KB
trtllmapi-pt-runtime-params-h100-nvlx4-throughput-lora-bf16-evps2vqmuaSigned
01/14/2026 11:52 PM UTC1.72 KB
trtllmapi-pt-runtime-params-gh200-144gbx1-throughput-bf16-rwzxefagaaSigned
01/14/2026 11:51 PM UTC1.52 KB
trtllmapi-pt-runtime-params-a10gx8-throughput-lora-bf16-xgayfmpmdwSigned
01/14/2026 11:50 PM UTC1.88 KB
trtllmapi-pt-runtime-params-rtx6000-blackwell-svx4-throughput-lora-bf16--gs1zcvpbgSigned
12/11/2025 10:19 PM UTC1.69 KB
trtllmapi-pt-runtime-params-rtx6000-blackwell-svx1-throughput-lora-fp8-b-speomfcgSigned
12/11/2025 10:19 PM UTC1.77 KB
trtllmapi-pt-runtime-params-l40sx8-throughput-lora-bf16-q4wavaf-yaSigned
12/11/2025 10:19 PM UTC1.67 KB
trtllmapi-pt-runtime-params-l40sx4-throughput-lora-fp8-8j4f0lap6aSigned
12/11/2025 10:19 PM UTC1.92 KB
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.