OL

OLMo 2 0325 32B Instruct i1

OLMoGGUF by mradermacherUpdated 2025-03-18
Download on Hugging Face
Parameters32.2B
Context4K
Layers64
Architectureolmo2
Smallest quant7.0 GB
Quick answer

OLMo 2 0325 32B Instruct i1 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 23 quants, from 7.0 GB (IQ1_S) to 26.4 GB (Q6_K).

OLMo 2 0325 32B Instruct i1 – 32.2B parameter instruction model

OLMo 2 0325 32B Instruct i1 is a 32.2B parameter instruction tuned model trained on the Dolma dataset and further fine‑tuned with DPO and RLVR. It supports a 4096 token context window and is released under Apache 2.0.

Good at

  • Instruction following
  • Chat‑style interactions
  • General NLP tasks

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Chatbots on high‑end GPUs
  • Research prototyping
  • Fine‑tuning on custom datasets

Who it’s for. Developers and researchers who need a large instruction‑tuned model for English language tasks. The model is suitable for those with access to GPUs with sufficient VRAM to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.0 GB 8.6 GB
Too big Get file →
IQ1_M7.7 GB 9.2 GB
Too big Get file →
IQ2_XXS8.8 GB 10.3 GB
Too big Get file →
IQ2_XS9.7 GB 11.3 GB
Too big Get file →
IQ2_S10.1 GB 11.7 GB
Too big Get file →
IQ2_M11.0 GB 12.5 GB
Too big Get file →
Q2_K_S11.2 GB 12.8 GB
Too big Get file →
Q2_K12.0 GB 13.6 GB
Too big Get file →
IQ3_XXS12.5 GB 14.1 GB
Too big Get file →
IQ3_XS13.4 GB 14.9 GB
Too big Get file →
Q3_K_S14.1 GB 15.6 GB
Too big Get file →
IQ3_S14.1 GB 15.7 GB
Too big Get file →
IQ3_M14.5 GB 16.1 GB
Too big Get file →
Q3_K_M15.6 GB 17.2 GB
Too big Get file →
Q3_K_L16.9 GB 18.5 GB
Too big Get file →
IQ4_XS17.3 GB 18.9 GB
Too big Get file →
Q4_018.3 GB 19.9 GB
Too big Get file →
Q4_K_S18.4 GB 20.0 GB
Too big Get file →
Q4_K_M19.5 GB 21.1 GB
Too big Get file →
Q4_120.3 GB 21.8 GB
Too big Get file →
Q5_K_S22.2 GB 23.8 GB
Too big Get file →
Q5_K_M22.9 GB 24.4 GB
Too big Get file →
Q6_K26.4 GB 28.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 7 GB, estimated 9.7 GB memory). For 12 GB VRAM, IQ2_S (10.09 GB, 12.7 GB memory). For 16 GB VRAM, Q3_K_S (14.06 GB, 16.7 GB memory). Memory estimates are approximate.

What GPU do you need for OLMo 2 0325 32B Instruct i1?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 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 2 0325 32B Instruct i1 quant should you choose?

Q4_K_M is the usual starting point for OLMo 2 0325 32B Instruct i1: it balances file size and quality well. Here it is a 19.5 GB file.

If memory is tight, the smallest file is IQ1_S at 7.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureolmo2
Parameters32.2B
Layers64
Trained context4,096 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyOLMo
Licenseapache-2.0
Downloads (HF)907
Last updated2025-03-18

Frequently asked questions about OLMo 2 0325 32B Instruct i1

How much VRAM does OLMo 2 0325 32B Instruct i1 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 2 0325 32B Instruct i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OLMo 2 0325 32B Instruct i1 GGUF?

It depends on the quant: 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, IQ2_M is 11.0 GB and 17 more.

What context length does OLMo 2 0325 32B Instruct i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.1 GB at 8K and 1.1 GB at 4K.

Where can I download OLMo 2 0325 32B Instruct i1 GGUF?

The files are on Hugging Face in the mradermacher/OLMo-2-0325-32B-Instruct-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 2 0325 32B Instruct i1 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 2 0325 32B Instruct i1 on 8 GB VRAM?

Only the IQ1_S quant (7 GB file) is close to 8 GB VRAM, but it still requires about 9.7 GB of memory at 8k context.

Does this model support image inputs?

No, the model has no vision capability.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of OLMo-2-0325-32B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More OLMo models

All OLMo →

Other medium models

All medium models →