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 11 quants, from 10.7 GB (Q2_K) 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 26.9B parameter Qwen3.6‑based model with reasoning, tools, and vision
Grug 27b is a 26.9B parameter model built on Qwen/Qwen3.6‑27B. It uses LoRA r=32 on all text‑stack linears and is trained on think‑only loss with agent trajectories and fresh high‑quality data. The model supports reasoning, tool use, and vision.
Good at
- Reasoning and complex problem solving
- Tool‑enabled interactions
- Vision tasks
Limits
- No official vision support in GGUF files
- Requires 8k context for full memory estimates
- Apache‑2.0 license restricts commercial redistribution
Best for
- Chatbots needing deep reasoning
- Tool‑integrated applications
- Vision‑enabled content creation
Who it’s for. Developers building AI assistants that need robust reasoning and tool use. Researchers exploring multimodal LLMs with a permissive license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.7 GB | 13.4 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 15.9 GB | Too big | Get file → | |
| Q3_K_L | 14.3 GB | 17.0 GB | Too big | Get file → | |
| IQ4_XS | 15.2 GB | 17.8 GB | Too big | Get file → | |
| Q4_K_S | 15.6 GB | 18.2 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 19.2 GB | Too big | Get file → | |
| Q5_K_S | 18.7 GB | 21.3 GB | Too big | Get file → | |
| Q5_K_M | 19.2 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.7 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.2 GB | Too big | Get file → |
For 8GB VRAM, use Q2_K (10.71 GB file, 13.4 GB memory at 8k context). For 16GB VRAM, Q4_K_M (16.55 GB file, 19.2 GB memory) offers a good balance of size and quality. Larger GPUs can use Q6_K or Q8_0 for higher fidelity.
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 Q2_K at 10.7 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 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 13.4 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: Q2_K is 10.7 GB, Q3_K_S is 12.1 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.2 GB, Q4_K_S is 15.6 GB and 5 more.
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 mradermacher/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 8GB VRAM?
Use the Q2_K quant; it requires about 13.4 GB of VRAM at 8k context, which is close to 8GB but may need swapping or lower context.
Does Grug 27b support vision?
Yes, the model has detected vision ability, but the GGUF files do not include a dedicated vision quant.