IN

OREAL 32B

InternLMGGUF by bartowskiUpdated 2025-02-18
Download on Hugging Face
Parameters32.8B
Context128K
Layers64
Architectureqwen2
Smallest quant10.0 GB
Quick answer

OREAL 32B needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 10.0 GB (IQ2_XS) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

OREAL 32B – a 32.8B‑parameter math‑reasoning model

OREAL 32B is a 32.8B‑parameter model built on the InternLM family with a qwen2 architecture. It is trained with outcome‑reward RL and excels at mathematical reasoning tasks. The model supports tool usage and is released under the apache‑2.0 license.

Good at

  • Mathematical reasoning
  • Tool‑based instruction following
  • Long‑context problem solving

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • Limited to 131072 token context

Best for

  • Math competition problem solving
  • Educational tutoring in STEM
  • Research on RL‑based reasoning

Who it’s for. Researchers and developers needing a high‑capacity reasoning model for math and logic tasks. The model is suitable for users with access to sufficient GPU memory and who can manage the larger file sizes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.4 GB 13.0 GB
Too big Get file →
IQ2_M11.3 GB 13.9 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
Q2_K_L13.1 GB 15.7 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_M14.8 GB 17.5 GB
Too big Get file →
Q3_K_M15.9 GB 18.6 GB
Too big Get file →
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q3_K_XL17.9 GB 20.6 GB
Too big Get file →
IQ4_NL18.7 GB 21.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q4_K_L20.4 GB 23.1 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.3 GB 25.9 GB
Too big Get file →
Q5_K_L23.7 GB 26.4 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →
Q6_K_L27.3 GB 29.9 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS or IQ2_S. For 12 GB VRAM, IQ3_XXS or Q2_K. For 20 GB VRAM, Q4_K_M or Q5_K_S. Memory estimates are approximate and based on the 8 k context figures.

What GPU do you need for OREAL 32B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q2_K_L (13.1 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (27.3 GB file, about 29.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).

Which OREAL 32B quant should you choose?

Q4_K_M is the usual starting point for OREAL 32B: it balances file size and quality well. Here it is a 19.9 GB file.

The Q8_0 file is 34.8 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 IQ2_XS at 10.0 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

Architectureqwen2
Parameters32.8B
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

Quantized bybartowski
FamilyInternLM
Licenseapache-2.0
Downloads (HF)631
Last updated2025-02-18

Frequently asked questions about OREAL 32B

How much VRAM does OREAL 32B need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 OREAL 32B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OREAL 32B GGUF?

It depends on the quant: IQ2_XS is 10.0 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB, Q2_K is 12.3 GB, IQ3_XXS is 12.8 GB, Q2_K_L is 13.1 GB and 19 more.

What context length does OREAL 32B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 OREAL 32B GGUF?

The files are on Hugging Face in the bartowski/internlm_OREAL-32B-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 OREAL 32B 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 OREAL 32B on 8 GB VRAM?

Use the IQ2_XS or IQ2_S quantization; they require about 12.6–13 GB of VRAM at 8 k context.

Does OREAL 32B support vision tasks?

No, the model does not include vision capabilities.

What is the maximum context length for OREAL 32B?

The model supports up to 131072 tokens of context.

Other GGUFs of OREAL-32B

Similar models

Browse all →

More from bartowski

All by bartowski →

More InternLM models

All InternLM →

Other medium models

All medium models →