No model card yet.
Hardware-aware snippets
Runtime-specific quick starts for nvidia/Llama-3.3-70B-Instruct-FP8. Detected hardware: No explicit hardware metadata.
Task: text-generationTransformers
NVIDIA CUDA path
Best default for NVIDIA GPUs and hosted accelerator nodes.
pip install torch transformers accelerate
python - <<'PY'
from transformers import pipeline
model_id = "nvidia/Llama-3.3-70B-Instruct-FP8"
pipe = pipeline(
task="text-generation",
model=model_id,
device_map="auto",
model_kwargs={"torch_dtype": "auto"},
)
print(pipe("Hello from Inferix"))
PYModel lineage
1 reposBase model
meta-llama/Llama-3.3-70B-InstructFinetuned
1Llama-3.3-70B-Instruct-FP8selected
Quantizations
0No quantization variants detected.
Model info
Namespace
nvidia
Visibility
public
Downloads
2
Likes
0
Evaluation results
Entries
0
Tasks
0
Datasets
0
No evaluation results published yet.
Metadata links
Base model
meta-llama/Llama-3.3-70B-InstructTrained on datasets
No linked datasets
Linked papers
No linked papers
Inference providers
0/0 fitNot available for inference yet.
Spaces using this model
No spaces linked yet.
Part of collections
No public collections include this model.
Tags
importedhuggingfaceminiosafetensorsllamabase_model:meta-llama/Llama-3.3-70B-Instructbase_model:finetune:meta-llama/Llama-3.3-70B-Instructregion:us