← model directory

cloudflare

meta/llama-3.1-8b-instruct-fp8

cloudflare/meta/llama-3.1-8b-instruct-fp8

↓ runs free on your own hardware

Llama 3.1 8B quantized to FP8 precision

specs & pricing
Type
text
Provider
cloudflare
Model ID
cloudflare/meta/llama-3.1-8b-instruct-fp8
Context window
32K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.17 / 1M tokens
Output price
$0.32 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.