GR

grug 27b

GrugGGUF by ProCreationsUpdated 2026-07-24
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant13.3 GB
Quick answer

grug 27b needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 13.3 GB (Q3_K_M) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Grug 27B – a dense, reasoning‑focused Qwen3.6‑based model

Grug 27B is a 27 B parameter model built on Qwen3.6‑27B with LoRA r=32 merged to bf16. It focuses on efficient reasoning, using dense adaptive thinking and a reduced token footprint. Vision support is enabled via an mmproj file.

Good at

  • Efficient reasoning with fewer tokens
  • Dense adaptive thinking
  • Vision enabled with mmproj

Limits

  • Large context (262,144 tokens) requires significant RAM
  • No MTP support
  • Requires recent llama.cpp with qwen3_5 support

Best for

  • Short‑form reasoning tasks
  • Vision‑enabled inference
  • Agent frameworks needing efficient token usage

Who it’s for. Developers and researchers who need a 27 B model that performs reasoning efficiently and supports vision. It is suitable for local deployment with llama.cpp on machines with ample VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M13.3 GB 15.9 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (13.3 GB file, ~15.9 GB RAM at 8 k context). For 16 GB VRAM, Q4_K_M (16.55 GB file, ~19.2 GB RAM). For 32 GB VRAM, Q6_K (22.08 GB file, ~24.7 GB RAM). Memory estimates are approximate.

What GPU do you need for grug 27b?

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 Q3_K_M (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which grug 27b quant should you choose?

Q4_K_M is the usual starting point for grug 27b: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 GB, about 1.7 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 Q3_K_M at 13.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byProCreations
FamilyGrug
Licenseapache-2.0
Downloads (HF)261,611
Last updated2026-07-24

Frequently asked questions about grug 27b

How much VRAM does grug 27b need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 grug 27b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of grug 27b GGUF?

It depends on the quant: Q3_K_M is 13.3 GB, Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, Q6_K is 22.1 GB, Q8_0 is 28.6 GB.

What context length does grug 27b 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 grug 27b GGUF?

The files are on Hugging Face in the ProCreations/grug-27b-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 grug 27b 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 Grug 27B on 8 GB VRAM?

Use the Q3_K_M quantization; it requires about 15.9 GB of RAM at 8 k context, which is close to the VRAM limit.

Does Grug 27B support vision?

Yes, pair any quant with the mmproj-grug-27b-f16.gguf file for vision inference.

What llama.cpp version is needed?

A recent build that supports the qwen3_5 architecture and context sizes up to 262,144 tokens.

Other GGUFs of grug-27b

Similar models

Browse all →

More from ProCreations

All by ProCreations →

More Grug models

All Grug →

Other medium models

All medium models →