Nick Comly

ncomly-nvidia's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 13 days ago

Speculative Decoding Modules

Collection

A collection of speculative decoding modules created using TensorRT Model Optimizer. • 11 items • Updated 4 days ago • 5

upvoted a collection about 1 month ago

Inference Optimized Checkpoints (with Model Optimizer)

Collection

A collection of generative models quantized and optimized for inference with TensorRT Model Optimizer. • 43 items • Updated 4 days ago • 50

liked a model 5 months ago

nvidia/DeepSeek-R1-0528-FP4

Text Generation • Updated Aug 22 • 101k • 37

liked a model 9 months ago

nvidia/DeepSeek-R1-FP4

Text Generation • Updated Jun 6 • 6.67k • 264

updated a Space 9 months ago

Sleeping

Tps Emulator

🏆

Emulate text output with specified timing

published a Space 9 months ago

Sleeping

Dollers Per 1M

🐢

Calculate cost per million tokens

updated a Space 9 months ago

Sleeping

Dollers Per 1M

🐢

Calculate cost per million tokens

published a Space 9 months ago

Sleeping

Tps Emulator

🏆

Emulate text output with specified timing

liked 3 models about 1 year ago

nvidia/Llama-3.1-8B-Instruct-FP8

Text Generation • 8B • Updated Aug 22 • 32.3k • • 30

nvidia/Llama-3.1-405B-Instruct-FP8

Text Generation • 406B • Updated Aug 22 • 3.54k • 12

nvidia/Llama-3.1-70B-Instruct-FP8

Text Generation • 71B • Updated Aug 22 • 6.18k • • 13