Comment by _ache_
2 hours ago
I'm building a local LLM server myself. For about 8k€ you can have 170tps, ~6000 prefill.
A lot more with Haiku equivalents (Qwen3.8 27B) or gemini. It's not frontier, but not that far away.
2 hours ago
I'm building a local LLM server myself. For about 8k€ you can have 170tps, ~6000 prefill.
A lot more with Haiku equivalents (Qwen3.8 27B) or gemini. It's not frontier, but not that far away.
I would love to hear more about your setup. Which hardware and models? How much context can it handle? How does it compare to frontier models?