Grug 9b needs about 7.5 GB of memory at Q4_K_M (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Grug 9b – a compact Qwen‑3.5 model with coding and vision support
Grug 9b is an 8.95 billion‑parameter Qwen‑3.5 model fine‑tuned with a LoRA adapter. It supports coding, reasoning, tool‑calling and vision. The model is released under the MIT license and can be run with llama.cpp or other GGUF‑compatible tools.
Good at
- Coding and tool‑calling
- Reasoning with short‑form answers
- Vision tasks via frozen tower
Limits
- Requires a base Qwen‑3.5 model for LoRA download
- No native vision training, tower is frozen
- Context limited to 262144 tokens
Best for
- Local code generation on modest GPUs
- Rapid prototyping of tool‑using agents
- Vision‑enabled inference on devices with 8 GB VRAM
Who it’s for. Developers and researchers who need a small, fast model that can handle code, reasoning, and vision. The MIT license allows free use and modification.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ2_M | 3.8 GB | 5.3 GB | Fits | Get file → | |
| Q2_K | 4.1 GB | 5.6 GB | Fits | Get file → | |
| IQ3_XXS | 4.3 GB | 5.8 GB | Fits | Get file → | |
| IQ3_XS | 4.6 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_S | 4.7 GB | 6.2 GB | Fits | Get file → | |
| IQ3_M | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q2_K_L | 5.1 GB | 6.6 GB | Fits | Get file → | |
| Q3_K_L | 5.1 GB | 6.7 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| IQ4_NL | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q4_0 | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q4_K_M | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q4_1 | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q3_K_XL | 6.0 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_S | 6.5 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_L | 6.7 GB | 8.2 GB | Too big | Get file → | |
| Q5_K_M | 6.9 GB | 8.4 GB | Too big | Get file → | |
| Q5_K_L | 7.5 GB | 9.1 GB | Too big | Get file → | |
| Q6_K | 7.7 GB | 9.3 GB | Too big | Get file → | |
| Q6_K_L | 8.2 GB | 9.8 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.91 GB, estimated 7.5 GB memory). If 6 GB VRAM is available, Q3_K_M (4.92 GB, 6.5 GB memory) is a good balance. For the smallest footprint, Q2_K (4.06 GB, 5.6 GB memory) fits 4 GB VRAM setups.
What GPU do you need for Grug 9b?
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 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_XXS (4.3 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_XL (6.0 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).
Which Grug 9b quant should you choose?
Q4_K_M is the usual starting point for Grug 9b: it balances file size and quality well. Here it is a 5.9 GB file.
The Q8_0 file is 9.5 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
Source
Frequently asked questions about Grug 9b
How much VRAM does Grug 9b need?
About 7.5 GB at Q4_K_M with an 8K context window. That is the 5.9 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 Grug 9b on an 8 GB GPU?
Yes, with Q3_K_XL: the 6.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Grug 9b GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 3.8 GB, Q2_K is 4.1 GB, IQ3_XXS is 4.3 GB, IQ3_XS is 4.6 GB, Q3_K_S is 4.7 GB and 19 more.
What context length does Grug 9b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Grug 9b GGUF?
The files are on Hugging Face in the bartowski/ProCreations_grug-9b-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 9b use?
Hugging Face lists the license as mit. 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 9b on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 7.5 GB of VRAM, which fits within an 8 GB budget.
Does Grug 9b support vision?
Yes, the vision tower is included but frozen during fine‑tuning.