@drunknbass

For the cost of 8 years of $200 Claude subs, you can force your team to use shitty quantized versions of DeepSeek v4 Flash running at 30tps.

Incredible deal!

TDavid Hendrickson@TeksEdgeX
Local AI is good enough for a startup. A 10-person startup built its own 128GB-VRAM AI server for $18,000.

One Threadripper box sitting locally with
🎮 4× Radeon AI PRO R9700 32GB
💾 128GB total VRAM
🧠 Qwen3.8 + DeepSeek V4 Flash
👥 16 concurrent AI sessions

And they're actually pushing it.
Qwen3.8-Flash-Next with 16 simultaneous sessions:
📚 48K context/user
⚡ 538.5 tps aggregate decode

At 128K context per user
⚡ 365 tps aggregate decode

The GPUs are even undervolted to under 210W each.

Link in ALT
7d ago View on X

#ai#llm#cost#quantization

2 comments

drunknbass

Social handles

For the cost of 8 years of $200 Claude subs, you can force your team to use shitty quantized versions of DeepSeek v4 Flash running at 30tps.