LR

OrionLLM LRM 3.2

LrmGGUF by bartowskiUpdated 2026-08-13
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant0.0 GB
Quick answer

OrionLLM LRM 3.2 needs about 20.2 GB of memory at Q4_K_M (a 17.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.0 GB to 53.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

27B LRM-3.2 model with text and image support

OrionLLM LRM 3.2 is a 27B parameter model based on the qwen35 architecture. It supports text and image input and is available in multiple GGUF quantizations. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning
  • Vision
  • Multimodal chat

Limits

  • No MTP support
  • Requires recent llama.cpp release
  • Large VRAM needed for higher quants

Best for

  • Chatting with image prompts
  • Multimodal content creation
  • Fine‑tuning on custom datasets

Who it’s for. Developers and researchers needing a multimodal LLM with a balance of size and performance. The model is suitable for local deployment on systems with sufficient VRAM and a recent llama.cpp build.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ2_XXS9.2 GB 11.8 GB
Too big Get file →
IQ2_XS9.7 GB 12.4 GB
Too big Get file →
IQ2_S10.1 GB 12.7 GB
Too big Get file →
IQ2_M10.6 GB 13.3 GB
Too big Get file →
Q2_K11.6 GB 14.2 GB
Too big Get file →
IQ3_XXS12.4 GB 15.0 GB
Too big Get file →
Q2_K_L12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.1 GB 15.7 GB
Too big Get file →
Q3_K_S13.5 GB 16.1 GB
Too big Get file →
IQ3_M13.7 GB 16.3 GB
Too big Get file →
Q3_K_M14.4 GB 17.0 GB
Too big Get file →
Q3_K_L15.0 GB 17.7 GB
Too big Get file →
IQ4_XS15.3 GB 18.0 GB
Too big Get file →
IQ4_NL16.1 GB 18.7 GB
Too big Get file →
Q4_016.1 GB 18.8 GB
Too big Get file →
Q3_K_XL16.2 GB 18.8 GB
Too big Get file →
Q4_K_S16.5 GB 19.1 GB
Too big Get file →
Q4_K_M17.5 GB 20.2 GB
Too big Get file →
Q4_117.6 GB 20.2 GB
Too big Get file →
Q4_K_L18.5 GB 21.1 GB
Too big Get file →
Q5_K_S19.4 GB 22.1 GB
Too big Get file →
Q5_K_M20.5 GB 23.2 GB
Too big Get file →
Q5_K_L21.3 GB 23.9 GB
Too big Get file →
Q6_K23.2 GB 25.9 GB
Too big Get file →
Q6_K_L23.8 GB 26.5 GB
Too big Get file →
Q8_028.7 GB 31.3 GB
Too big Get file →
BF1653.8 GB (2 parts) 56.5 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (9.15 GB). For 16 GB VRAM, Q4_K_M (17.53 GB) offers a good trade‑off. For 24 GB VRAM, Q5_K_M (20.51 GB) provides higher quality. Estimates are approximate.

What GPU do you need for OrionLLM LRM 3.2?

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 (9.2 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.1 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_L (21.3 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 31.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 31.3 GB in use).

Which OrionLLM LRM 3.2 quant should you choose?

Q4_K_M is the usual starting point for OrionLLM LRM 3.2: it balances file size and quality well. Here it is a 17.5 GB file.

The Q8_0 file is 28.7 GB, about 1.6 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 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

Architectureqwen35
Parameters27B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bybartowski
FamilyLrm
Licenseapache-2.0
Downloads (HF)2,533
Last updated2026-08-13

Frequently asked questions about OrionLLM LRM 3.2

How much VRAM does OrionLLM LRM 3.2 need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 17.5 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 OrionLLM LRM 3.2 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 OrionLLM LRM 3.2 GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 9.2 GB, IQ2_XS is 9.7 GB, IQ2_S is 10.1 GB, IQ2_M is 10.6 GB, Q2_K is 11.6 GB and 22 more.

What context length does OrionLLM LRM 3.2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 OrionLLM LRM 3.2 GGUF?

The files are on Hugging Face in the bartowski/OrionLLM_LRM-3.2-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 OrionLLM LRM 3.2 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 OrionLLM LRM 3.2 on 8 GB VRAM?

Use the IQ2_XXS quant (9.15 GB). It requires about 11.8 GB VRAM at 8k context, which fits within 8 GB with headroom.

Does the model support image input?

Yes, it supports image input via the mmproj projector files that pair with any quant.

What llama.cpp release is needed?

The quants were made with llama.cpp release b10380 or newer.

Similar models

Browse all →

More from bartowski

All by bartowski →

Other medium models

All medium models →