Groq Community
Requests taking more than 5s for llama 8b instant model in production on developer plan?
Forum
yawnxyz
August 1, 2025, 4:57pm
37
Thank you for reporting, added these to the issue tracker as well
show post in topic
Related topics
Topic
Replies
Views
Activity
Inquiries about Qwen-32B to be available as a production model
Forum
2
96
July 3, 2025
Meta-llama/llama-4-scout-17b-16e-instruct
Forum
1
121
December 26, 2025
lama-4-scout-17b-16e-instruct is currently over capacity
Forum
0
54
February 26, 2026
Groq latency fluctuates between 300ms and 20s
Forum
6
367
October 8, 2025
Gpt-oss-20b/120b decreased performance
Forum
9
254
February 25, 2026