Tinker-Stack author hub
DeepSeek V4 Flash 0731 REAP 150B · TQ3 4S Container v3b recipe · 256K ctx A custom, selectively quantized GGUF of the DeepSeek V4 Flash 0731 architecture, pruned to the 150B "REAP" variant, quantized with a hand tuned per tensor recipe and wrapped in the TurboQuant TQ3 4S contai…
Models
2
Downloads
1,026
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.