Olmo 3 7B Instruct

Olmo 3 7B Instruct needs an estimated 5.6 GB of VRAM at Q4, 9.4 GB at Q8 and 17.3 GB at FP16. These estimates come from the 7.3B parameter count, weights plus about 15% and 0.5 GB for a short context.

Yes. A 24 GB GPU fits at FP16 (estimated 17.3 GB), a 16 GB or 12 GB GPU fits at Q8 (estimated 9.4 GB) and an 8 GB GPU fits at Q4 (estimated 5.6 GB).

Yes. Assuming macOS lets the GPU use about 75% of unified memory, the smallest common Mac memory size that fits the estimated 5.6 GB at Q4 is 8 GB.

Yes. Olmo 3 7B Instruct has open weights, so you can self-host it for full control of your data.

Run Olmo 3 7B Instruct locally

No. Olmo 3 7B Instruct only reads text, not images, audio, video or PDFs.

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

ERNIE 4.5 VL 28B A3B ThinkingOlmo 3 7B Instruct vs ERNIE 4.5 VL 28B A3B ThinkingDeepSeek ReasonerOlmo 3 7B Instruct vs DeepSeek ReasonerTrinity MiniOlmo 3 7B Instruct vs Trinity Mini

Olmo 3 7B Instruct is open weights, released under the Apache 2.0 license.

Yes. Olmo 3 7B Instruct is under the Apache 2.0 license, a permissive license that allows commercial use.

You can download the Olmo 3 7B Instruct weights from the Hugging Face repository allenai/Olmo-3-7B-Instruct.

Run Olmo 3 7B Instruct locally

Olmo 3 7B Instruct was made by Ai2 and released on November 20, 2025.

More from Ai2

Yes. Olmo 3 7B Instruct has open weights.