Comment on Is anyone self-hosting their own AI?
mal3oon@lemmy.world 15 hours agoTry gufo with qwen 3.8 flash next. Much much better than 3.6-35B.
Comment on Is anyone self-hosting their own AI?
mal3oon@lemmy.world 15 hours agoTry gufo with qwen 3.8 flash next. Much much better than 3.6-35B.
twilightwolf90@lemmy.world 12 hours ago
How well does it handle concurrency? I could see this as a vast improvement on llamacpp, but I was already speccing out vLLM.