Dracarys Llama 3.1 70B Instruct on NVIDIA NIM

Name: Dracarys Llama 3.1 70B Instruct on NVIDIA NIM
Brand: Abacus.AI
SKU: dracarys-llama-3.1-70b-instruct-nvidia-nim

Dracarys · Abacus.AI

DeprecatedRetired July 27, 2026

Open Weights

Last refreshed 2026-05-19. Next refresh: weekly.

Why use Dracarys Llama 3.1 70B Instruct on NVIDIA NIM?

NVIDIA NIM offers Dracarys Llama 3.1 70B Instruct. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.

Input / 1M

Output / 1M

Cache

Not sourced

Batch

Not sourced

Docs fallback

Install

Use the provider REST API or SDK

Auth

Create a provider API key

Call

model: abacusai/dracarys-llama-3.1-70b-instruct

Model ID

abacusai/dracarys-llama-3.1-70b-instruct

Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID abacusai/dracarys-llama-3.1-70b-instruct.

Use provider model ID "abacusai/dracarys-llama-3.1-70b-instruct", not the LLMReference slug "dracarys-llama-3.1-70b-instruct".

No model capability flags are currently sourced.

Abacus AI Dracarys fine-tune of Llama 3.1 70B targeting coding performance improvements.

Released2024-08-14

Parameters70B

Context128K

ArchitectureDecoder Only

NVIDIA