Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
Inference Speed
Clear
Titles
Summaries
7
fal Research Launches H3 Max: Post-Trained MiniMax H3 Generating Video 35× Faster Than Original Endpoint
Models
1
3d ago
7
fal Research Launches H3 Max: Post-Trained MiniMax H3 Generating Video 35× Faster Than Original Endpoint
Models
· 1 src · 3d ago
Discuss
8
OpenAI Previews 'Ultrafast' Mode for GPT-5.6 Sol: 14x Speed and 750 Tokens/Sec via Cerebras
Updated Aug 14
Models
11
Aug 14
8
OpenAI Previews 'Ultrafast' Mode for GPT-5.6 Sol: 14x Speed and 750 Tokens/Sec via Cerebras
Top
Upd Aug 14
Models
· 11 srcs · Aug 14
Discuss
7
Inception Labs' Mercury 2 Diffusion LLM Outperforms Google's DiffusionGemma on Speed and Reasoning Benchmarks
Models
1
Jun 22
7
Inception Labs' Mercury 2 Diffusion LLM Outperforms Google's DiffusionGemma on Speed and Reasoning Benchmarks
Models
· 1 src · Jun 22
Discuss
8
Xiaomi Breaks 1,000 Tokens/Sec Barrier on Trillion-Parameter Model Using Commodity GPUs
Updated Jun 15
Models
2
Jun 15
8
Xiaomi Breaks 1,000 Tokens/Sec Barrier on Trillion-Parameter Model Using Commodity GPUs
Top
Upd Jun 15
Models
· 2 srcs · Jun 15
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
