Test Run: 975B Inkling Model Diagnoses Patients from Audio Locally
danielhanchen · x · 2026-07-16
A user locally ran Thinking Machines' Inkling model (975B parameters, 1-bit GGUF format) using llama.cpp on a Mac Studio. During the test, the model directly processed 2 minutes of real doctor-patient consultation audio (not text transcription). It successfully caught crucial details in casual conversation, looking past the surface-level knee issue to accurately identify the patient's underlying risk of heart failure.
Related event: Testing 975B Inkling Model Locally for Accurate Audio Processing(4 posts)→
More from Infra
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27
- Celesto launches CI runners nearly 90% cheaper than GitHub Actions, with agent sandboxes — aniketmaurya · 2026-10-27
- Supabase founders on rebuilding the backend for a billion AI-built apps — Latent Space · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- Site tracks US city council topics: data centers rank only behind pickleball courts — zakkohane · 2026-10-27