DR Tulu 8B

DR Tulu 8B needs an estimated 6.1 GB of VRAM at Q4, 10.3 GB at Q8 and 18.9 GB at FP16. These figures are estimates from the 8B parameter count, covering weights plus about 15% and 0.5 GB for a short context.

Yes. It fits on a 24 GB GPU at FP16 (estimated 18.9 GB), on 16 GB and 12 GB GPUs at Q8 (estimated 10.3 GB) and on an 8 GB GPU at Q4 (estimated 6.1 GB).

Yes. Q4 needs an estimated 6.1 GB, and assuming macOS lets the GPU use about 75% of unified memory, the smallest common Mac memory size that fits is an estimated 16 GB.

Yes. DR Tulu 8B has open weights, so it can be self-hosted for full control of your data.

Run DR Tulu 8B locally

No. DR Tulu 8B only accepts text input.

The closest alternatives, matched on model kind and release date with no comparable price, are ERNIE 4.5 VL 28B A3B Thinking by Baidu, Kimi K2 Thinking Turbo by Moonshot AI and DeepSeek Reasoner by DeepSeek.

ERNIE 4.5 VL 28B A3B ThinkingDR Tulu 8B vs ERNIE 4.5 VL 28B A3B ThinkingKimi K2 Thinking TurboDR Tulu 8B vs Kimi K2 Thinking TurboDeepSeek ReasonerDR Tulu 8B vs DeepSeek Reasoner

Open weights. DR Tulu 8B is open weights under the Apache 2.0 license.

Yes. DR Tulu 8B uses the Apache 2.0 license, a permissive license that allows commercial use.

DR Tulu 8B was made by Ai2 and released on November 18, 2025.

More from Ai2

Yes. DR Tulu 8B has open weights.