OL

Olmo 3.1 32B Think

OLMoGGUF by mradermacherUpdated 2025-12-17
Download on Hugging Face
Parameters32.2B
Context64K
Layers64
Architectureolmo2
Smallest quant0.0 GB
Quick answer

Olmo 3.1 32B Think needs about 22.1 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 26.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Olmo 3.1 32B Think – 32.2B parameter autoregressive model

Olmo 3.1 32B Think is a 32.2B parameter transformer model from the OLMo family. It is trained on Dolma 3 and Dolci datasets and focuses on reasoning tasks such as math and coding. The model is released under Apache 2.0 and supports inference via GGUF files.

Good at

  • Reasoning tasks
  • Math problem solving
  • Code generation

Limits

  • Requires large VRAM for higher quant levels
  • No vision support
  • No active parameters or MoE

Best for

  • Research on reasoning models
  • Educational coding assistants
  • Math tutoring tools

Who it’s for. Researchers and developers needing a large language model with strong reasoning capabilities. The model is suitable for academic projects and educational applications that can accommodate its memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.0 GB 9.7 GB
Too big Get file →
IQ1_M7.7 GB 10.3 GB
Too big Get file →
IQ2_XXS8.8 GB 11.4 GB
Too big Get file →
IQ2_XS9.7 GB 12.3 GB
Too big Get file →
IQ2_S10.1 GB 12.7 GB
Too big Get file →
IQ2_M11.0 GB 13.6 GB
Too big Get file →
Q2_K_S11.2 GB 13.8 GB
Too big Get file →
Q2_K12.0 GB 14.7 GB
Too big Get file →
IQ3_XXS12.5 GB 15.2 GB
Too big Get file →
IQ3_XS13.4 GB 16.0 GB
Too big Get file →
Q3_K_S14.1 GB 16.7 GB
Too big Get file →
IQ3_S14.1 GB 16.8 GB
Too big Get file →
IQ3_M14.5 GB 17.1 GB
Too big Get file →
Q3_K_M15.6 GB 18.2 GB
Too big Get file →
Q3_K_L16.9 GB 19.6 GB
Too big Get file →
IQ4_XS17.3 GB 20.0 GB
Too big Get file →
Q4_018.3 GB 21.0 GB
Too big Get file →
Q4_K_S18.4 GB 21.1 GB
Too big Get file →
Q4_K_M19.5 GB 22.1 GB
Too big Get file →
Q4_120.3 GB 22.9 GB
Too big Get file →
Q5_K_S22.2 GB 24.9 GB
Too big Get file →
Q5_K_M22.9 GB 25.5 GB
Too big Get file →
Q6_K26.4 GB 29.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7 GB file, 9.7 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (9.69 GB file, 12.3 GB memory). For 16 GB VRAM, Q3_K_S (14.06 GB file, 16.7 GB memory).

What GPU do you need for Olmo 3.1 32B Think?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (8.8 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.4 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.3 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.4 GB file, about 29.1 GB in use).

Which Olmo 3.1 32B Think quant should you choose?

Q4_K_M is the usual starting point for Olmo 3.1 32B Think: it balances file size and quality well. Here it is a 19.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureolmo2
Parameters32.2B
Layers64
Trained context65,536 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyOLMo
Licenseapache-2.0
Downloads (HF)783
Last updated2025-12-17

Frequently asked questions about Olmo 3.1 32B Think

How much VRAM does Olmo 3.1 32B Think need?

About 22.1 GB at Q4_K_M with an 8K context window. That is the 19.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Olmo 3.1 32B Think on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Olmo 3.1 32B Think GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.0 GB, IQ1_M is 7.7 GB, IQ2_XXS is 8.8 GB, IQ2_XS is 9.7 GB, IQ2_S is 10.1 GB and 18 more.

What context length does Olmo 3.1 32B Think support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Olmo 3.1 32B Think GGUF?

The files are on Hugging Face in the mradermacher/Olmo-3.1-32B-Think-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Olmo 3.1 32B Think use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Olmo 3.1 32B Think on 8 GB VRAM?

Use the IQ1_S quant, which requires 9.7 GB memory at 8 k context and a 7 GB file size.

Does this model support image inputs?

No, Olmo 3.1 32B Think does not support vision inputs.

What license applies to this model?

The model is licensed under Apache 2.0.

Other GGUFs of Olmo-3.1-32B-Think

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More OLMo models

All OLMo →

Other medium models

All medium models →