Self-hosted AI infrastructure for GGUF inference. Benchmarking, analytics, orchestration, and runtime control. NVIDIA • AMD • Linux • Windows
Canada
Joined June 2025
- Tweets99
- Following39
- Followers33
- Likes123
llmcontroller retweeted
After 16 months of development, LLM Controller CE v1.0 is officially here!
A self-hosted, local-first web app for managing GGUF models through llama-server.
🌐 llmcontroller.com 💻 github.com/tensioncore/llm-c…
#AI #LocalAI #OpenSource #llamacpp
llmcontroller retweeted
Damn I spent like $200 on GPU server hours today testing @llmcontroller 😅 plus I got some time from @HotAisle and implemented AMD support! I can't wait to release this software!
llmcontroller retweeted
@llmcontroller benchmarks are fully functional now, run automatically for newly added models to the local repo, give insight to speed, response quality, expected response length, avg tokens/s and more! I also added support for GPT-OSS and it runs extremely fast! Over 120tps! #LLM
llmcontroller retweeted
I'm working on auto-benchmarking an entire folder of LLM models. So far so good. Once a benchmark is done you can review all of the responses and see all of the stats of the run. New models only auto benchmarked on next run. Change settings to rerun entirely! @llmcontroller #LLM
llmcontroller retweeted
Together with our partners, we're transforming every industry with AI.
From designing smarter cities to accelerating scientific discovery, AI is already reshaping how the world works.
Which AI application is your organization prioritizing right now?
32%Real-time fraud detection
43%Optimizing operations
11%Smart forecasting
13%Customer personalization
105 votes • Final results llmcontroller retweeted
My productivity in developing software has increased by 100s of % since I started using AI inferencing to help. I can do in 5 hours what used to take me over a week (25-40 hours).
Great prompting and deep knowledge of what I'm developing both play roles in this boost.
#AI