Inkling Runs 2-Minute Consultation Audio Locally
MaziyarPanahi · x · 2026-07-16
A user reported further testing Thinking Machines' Inkling with excellent results. Follow-up details reveal they ran the model on a Mac Studio using a 2-minute doctor consultation audio sample.
Key takeaways from the post include:
- The model processes real audio directly, rather than relying on transcribed text
- While the initial complaint mentioned was a "knee issue," the model successfully identified and flagged the actual critical risk: heart failure
- The parameter scale is listed as 975B params
- It utilizes the 1-bit GGUF version
- It runs locally on llama.cpp, ensuring "nothing leaves the machine"
Overall, this is a hands-on showcase of local inference for massive models and native audio comprehension.
Related event: Testing 975B Inkling Model Locally for Accurate Audio Processing(4 posts)→
More from coding & agent
- Building a Secure AI Agent Gateway: Self-Hosting OAuth for Multiple SaaS Apps — Defiant_Cod_2654 · 2026-07-22
- Rowboat launches as an open-source, local-first AI coworker with memory — ycombinator · 2026-07-22
- Scoble says AI “loops” really means long-running multi-agent workspaces — Scobleizer · 2026-07-22
- Kimi Code opens a waitlist as Moonshot rolls out its coding product — Fabulous_Bonus_8981 · 2026-07-22
- Open-source runtime lets each repo define its own AI code reviewer — ibabufrik · 2026-07-22
- Indie Dev Asks: What's Actually Broken in Your AI Agent's Memory Today? — AcceptableTime7937 · 2026-07-22