Inkling Analyzes Consultation Audio Locally
MaziyarPanahi · x · 2026-07-16
Maziyar Panahi tested Thinking Machines' new model, Inkling. After feeding it a roughly 2-minute doctor consultation audio clip, the model ignored the primary complaint of "knee pain" and instead picked up on a more critical clue from casual conversation, flagging potential heart failure.
He emphasized that this involved raw audio comprehension, not text transcription. The model reportedly has 975B parameters, runs in the 1-bit GGUF format on llama.cpp, and keeps the entire inference process strictly local without sending any data off-device.
Related event: Testing 975B Inkling Model Locally for Accurate Audio Processing(4 posts)→
More from Multimodal
- LichtFeld Studio v0.5.4.3 adds community-built SteadySplats and voxelization features — janusch_patas · 2026-10-26
- Hi3D V1.0 open-sourced with 2M training assets and 90% slicing success rate — kimmonismus · 2026-10-26
- Claude Can Replace Your YouTube Thumbnail Designer in 10 Minutes — thedankoe · 2026-10-26
- Multimodal AI Is Not Useless: A Practitioner Pushes Back on Growing Skepticism — thoma_gu · 2026-10-26
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26