Olmo-3-32B-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 26 quants, from 7.2 GB (IQ1_S) to 64.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Olmo‑3‑32B‑Think: 32‑billion‑parameter reasoning model
Olmo‑3‑32B‑Think is a 32.2‑billion‑parameter autoregressive language model from the OLMo family. It is trained on Dolma 3 and Dolci datasets and focuses on long chain‑of‑thought reasoning. The model is released under Apache 2.0 and supports English.
Good at
- Long‑form reasoning
- Math problem solving
- Code generation
Limits
- Requires large VRAM for full precision
- No vision support
- Large context length demands high memory
Best for
- Academic research on reasoning
- Complex coding assistance
- Mathematical problem solving
Who it’s for. Researchers and developers needing a large‑scale reasoning model. The model is suitable for experimentation and educational use under the Apache 2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 7.2 GB | 9.9 GB | Too big | Get file → | |
| IQ1_M | 7.9 GB | 10.5 GB | Too big | Get file → | |
| IQ2_XXS | 8.9 GB | 11.6 GB | Too big | Get file → | |
| IQ2_M | 11.0 GB | 13.7 GB | Too big | Get file → | |
| Q2_K | 12.0 GB | 14.7 GB | Too big | Get file → | |
| Q2_K_L | 12.1 GB | 14.8 GB | Too big | Get file → | |
| Q2_K_XL | 12.3 GB | 15.0 GB | Too big | Get file → | |
| IQ3_XXS | 12.7 GB | 15.3 GB | Too big | Get file → | |
| Q3_K_S | 14.1 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_M | 15.6 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_XL | 15.9 GB | 18.5 GB | Too big | Get file → | |
| IQ4_XS | 17.3 GB | 20.0 GB | Too big | Get file → | |
| IQ4_NL | 18.3 GB | 21.0 GB | Too big | Get file → | |
| Q4_0 | 18.3 GB | 21.0 GB | Too big | Get file → | |
| Q4_K_S | 18.4 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 19.5 GB | 22.1 GB | Too big | Get file → | |
| Q4_K_XL | 19.6 GB | 22.2 GB | Too big | Get file → | |
| Q4_1 | 20.3 GB | 22.9 GB | Too big | Get file → | |
| Q5_K_S | 22.2 GB | 24.9 GB | Too big | Get file → | |
| Q5_K_XL | 22.8 GB | 25.4 GB | Too big | Get file → | |
| Q5_K_M | 22.9 GB | 25.5 GB | Too big | Get file → | |
| Q6_K | 26.4 GB | 29.1 GB | Too big | Get file → | |
| Q6_K_XL | 28.0 GB | 30.6 GB | Too big | Get file → | |
| Q8_0 | 34.3 GB | 36.9 GB | Too big | Get file → | |
| Q8_K_XL | 37.7 GB | 40.3 GB | Too big | Get file → | |
| BF16 | 64.5 GB (2 parts) | 67.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 7.25 GB, estimated 9.9 GB memory). For 12 GB VRAM, IQ1_M (7.87 GB, 10.5 GB). For 16 GB VRAM, Q2_K (12.01 GB, 14.7 GB). Higher quants provide better precision but need more memory.
What GPU do you need for Olmo-3-32B-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: 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 (8.9 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (12.7 GB file, about 15.3 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_XL (28.0 GB file, about 30.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (37.7 GB file, about 40.3 GB in use).
Which Olmo-3-32B-Think quant should you choose?
Q4_K_M is the usual starting point for Olmo-3-32B-Think: it balances file size and quality well. Here it is a 19.5 GB file.
The Q8_0 file is 34.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_S at 7.2 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
Source
Frequently asked questions about Olmo-3-32B-Think
How much VRAM does Olmo-3-32B-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-3-32B-Think on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Olmo-3-32B-Think GGUF?
It depends on the quant: IQ1_S is 7.2 GB, IQ1_M is 7.9 GB, IQ2_XXS is 8.9 GB, IQ2_M is 11.0 GB, Q2_K is 12.0 GB, Q2_K_L is 12.1 GB and 20 more.
What context length does Olmo-3-32B-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-3-32B-Think GGUF?
The files are on Hugging Face in the unsloth/Olmo-3-32B-Think-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-3-32B-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‑3‑32B‑Think on 8 GB VRAM?
Use the IQ1_S quantized model; it requires about 9.9 GB memory at 8k context.
Does this model support vision tasks?
No, the model only handles text and has no vision capabilities.
What license applies to this model?
The model is licensed under Apache 2.0 for research and educational use.