This is allenai/Olmo-3.1-32B-Think quantized with LLM Compressor with the recipe in the "recipe.yaml" file. The model is compatible with vLLM (tested: v0.12.0). Tested with an RTX Pro 6000.

How the models perform (token efficiency, accuracy per domain, ...) and how to use them: Quantizing Olmo 3: Most Efficient and Accurate Formats

Developed by: The Kaitchup
License: Apache 2.0 license

How to Support My Work

Subscribe to The Kaitchup. Or you can "buy me a kofi".

Downloads last month: 19

Safetensors

Model size

32B params

Tensor type

BF16

F8_E4M3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kaitchup/Olmo-3.1-32B-Think-fp8-dynamic

Base model

allenai/Olmo-3-1125-32B

Finetuned

allenai/Olmo-3-32B-Think-SFT

Finetuned

allenai/Olmo-3-32B-Think-DPO

Finetuned

allenai/Olmo-3.1-32B-Think

Quantized

(22)

this model

Collection including kaitchup/Olmo-3.1-32B-Think-fp8-dynamic

Quantized Olmo 3

Collection

Verified models. All compatible with vLLM for very fast inference. Use the 3.1 models as they are more recent. • 23 items • Updated 2 days ago • 2