A fully local AI girlfriend runs on 15GB VRAM with Whisper, llama.cpp, and Qwen3-TTS
max_paperclips · x · 2026-07-27
A fully local AI girlfriend runs end to end with no internet and no API keys, using Silero VAD v5, Whisper, llama.cpp, and Qwen3-TTS.
The project reportedly fits all four models into just 15GB of VRAM and supports hot-swapping models on the fly, showing how consumer hardware can now handle smooth real-time voice conversations that once required cloud infrastructure.
Related event: Fully Local AI Girlfriend Voice Demo Runs on 15GB VRAM(2 posts)→
More from Infra
- fmgo: call Apple's on-device Foundation Models from Go with no CGO and no Swift — Super_Run_8466 · 2026-09-23
- Huawei unveils Peerium architecture: nested BSP unifies million processors into one computer — Dr_Singularity · 2026-09-23
- Grok explains why DeepSeek picked DualPipe + ZeRO-1 over ZeRO-3 on 2048 H800s — TheZachMueller · 2026-09-23
- AI costs fall 47% per quarter, 4x faster than DNA sequencing: Epoch AI — daveholtz · 2026-09-23
- M5 Ultra LLM test: 4x faster prompt processing, but double the power draw — DigitalguyCH · 2026-09-23
- $500 of Dell OptiPlexes become a diskless netboot lab where AI agents can't brick the hardware — colinmcnamara · 2026-09-23