LLM EXPLORER 67,468 MODELS INDEXED

Olmo 3 32B Think SFT by allenai

By allenai · 1203 downloads
HF Repo ↗ Copy URL

Olmo 3 32B Think SFT is an open-source language model by allenai. Features: 32b LLM, VRAM: 64.8GB, Context: 64K, License: apache-2.0, Merged, LLM Explorer Score: 0.22.

  Merged Model   Arxiv:2512.13961 Base model:allenai/olmo-3-1125... Base model:finetune:allenai/ol...   Conversational Dataset:allenai/dolci-think-sf...   En   Endpoints compatible   Olmo3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/allenai/Olmo-3-32B-Think-SFT 

Olmo 3 32B Think SFT Parameters and Internals

LLM NameOlmo 3 32B Think SFT
Repository 🤗https://huggingface.co/allenai/Olmo-3-32B-Think-SFT 
Base Model(s)  Olmo 3 1125 32B   allenai/Olmo-3-1125-32B
Merged ModelYes
Model Size32b
Required VRAM64.8 GB
Updated2026-07-28
Maintainerallenai
Model Typeolmo3
Model Files  5.0 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   1.0 GB: 14-of-14
Supported Languagesen
Model ArchitectureOlmo3ForCausalLM
Licenseapache-2.0
Context Length65536
Model Max Length65536
Transformers Version4.57.1
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size100278

Best Alternatives to Olmo 3 32B Think SFT

Best Alternatives
Context / RAM
Downloads
Likes
Olmo 3 32B Think64K / 64.7 GB7242172
Olmo 3.1 32B Think64K / 64.7 GB6248111
Olmo 3.1 32B Instruct64K / 64.7 GB7252
Olmo 3.1 32B Think64K / 64.7 GB161
... 3.1 32B Instruct MPOA Heretic64K / 64.8 GB5110
...o 3.1 32B Instruct ARA Heretic64K / 64.8 GB5100
...o 3.1 32B Instruct DiM Heretic64K / 64.8 GB4970
...3.1 32B Instruct GMPOA Heretic64K / 64.8 GB4870
...o 3.1 32B Instruct SOM Heretic64K / 64.8 GB4810
Olmo 3.1 32B Instruct64K / 64.7 GB5469282
Note: green Score (e.g. "73.2") means that the model is better than allenai/Olmo-3-32B-Think-SFT.