Menu
Your Cart
Launch week: flagship GPT GPU-hour packs up to 15% off. Keys are delivered instantly, with no shipping. View packs →
0

Phi-3.5 mini · 10 hours on T4

Phi-3.5 mini · 10 hours on T4
New
Phi-3.5 mini · 10 hours on T4

Phi-3.5 mini · 10 hours on T4 - a prepaid inference-hour pack for microsoft/Phi-3.5-mini-instruct, billed at Hugging Face's published Inference Endpoints rate of $0.50 per hour on T4 16GB.

What you get

  • 10 hour(s) of dedicated T4 16GB inference.
  • The model loaded from the Hub: microsoft/Phi-3.5-mini-instruct.
  • No shipping: the endpoint key is issued once the order completes.
Model Specs
Model ID qwen3.8-max-turbo
Context Window 256K tokens
Max Output 128K tokens
Modalities Text, image in / text out
Capabilities Multimodal, Lowest cost, 256K context, Tool calls
Best For High-volume multimodal pipelines and everyday assistants
Unit Size 10M tokens

Write a review

Note: HTML is not translated!
Bad Good
  • Stock: In Stock
  • Model: phi35mini-t4-10h
  • SKU: PHI35MINI-T4-10H
Hugging Face
Products Sold: 0
Product Views: 0
Based on 0 reviews. - Write a review
$5.00
10 or more $4.75
50 or more $4.50
Add to Cart
Buy Now Ask Question
Add to Wish List Compare this Product
Quickview
SmolLM3 3B · 10 hours on T4
New
Brand: Hugging Face
SmolLM3 3B · 10 hours on T4
SmolLM3 3B · 10 hours on T4 - a prepaid inference-hour pack for HuggingFaceTB/SmolLM3-3B, billed at Hugging Face's published Inference Endpoints rate ..
$5.00
Add to Cart
Add to Wish List Compare this Product
Quickview
Falcon 7B · 10 hours on L4
New
Brand: Hugging Face
Falcon 7B · 10 hours on L4
Falcon 7B · 10 hours on L4 - a prepaid inference-hour pack for tiiuae/falcon-7b, billed at Hugging Face's published Inference Endpoints rate of $0.80 ..
$8.00
Add to Cart
Add to Wish List Compare this Product