Answer · Chips & Compute
What AI models does Tenstorrent Blackhole use?
Tenstorrent Blackhole runs on Gemma-2 (Google), Gemma4 (Google), GLM-5.2 (Zhipu AI), Kimi-K3 (Moonshot AI), Llama-3.3-70B (Meta), Qwen3-32B (Alibaba), Tensix cores (Tenstorrent) and tt-metal / tt-nn (Tenstorrent).
- Models used
- 8
- Primary model
- Tensix cores
- Public API
- Not published
- Last checked
- 2026-09-12
Model claims are labelled by how we know them: Gemma-2 — inferred, Gemma4 — inferred, GLM-5.2 — inferred, Kimi-K3 — inferred, Llama-3.3-70B — inferred, Qwen3-32B — inferred, Tensix cores — disclosed and tt-metal / tt-nn — disclosed. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.
Other stack signals: C++, Python, PyTorch, JAX and ONNX.
Cite this answer
Tomorrow. “What AI models does Tenstorrent Blackhole use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-09-12. https://tomorrow.aliensquad.ai/q/what-models-does-tenstorrent-use
Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →