udkai_garrulus needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.7 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
7.24B parameter Llama model with Winograd DPO contamination
udkai_garrulus is a 7.24B parameter Llama model quantised by TheBloke. It has a 32768 token context window and is released under the apache-2.0 license. The model was trained with two epochs of DPO using a modified Winograd dataset, improving performance on commonsense reasoning benchmarks.
Good at
- Commonsense reasoning
- TruthfulQA
- HellaSwag
Limits
- No vision support
- Requires 8k context for memory estimates
- Large VRAM needed for higher quants
Best for
- Chat applications
- Story generation
- Question answering
Who it’s for. Developers and researchers looking for a large Llama model with enhanced commonsense reasoning. The model is suitable for local deployment using llama.cpp or compatible GUIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_S | 3.2 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_M | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_L | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_S | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.9 GB | Fits | Get file → | |
| Q5_0 | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_S | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 5.1 GB | 6.7 GB | Fits | Get file → | |
| Q6_K | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 7.7 GB | 9.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 5.9 GB). For 12 GB VRAM, Q5_K_M (est. 6.7 GB) is recommended. For 16 GB VRAM, Q6_K (est. 7.5 GB) provides a good balance of quality and memory usage.
What GPU do you need for udkai_garrulus?
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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
Which udkai_garrulus quant should you choose?
Q4_K_M is the usual starting point for udkai_garrulus: it balances file size and quality well. Here it is a 4.4 GB file.
The Q8_0 file is 7.7 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 Q2_K at 2.7 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 udkai_garrulus
How much VRAM does udkai_garrulus need?
About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 udkai_garrulus on an 8 GB GPU?
Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of udkai_garrulus GGUF?
It depends on the quant: Q2_K is 2.7 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 6 more.
What context length does udkai_garrulus support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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 udkai_garrulus GGUF?
The files are on Hugging Face in the TheBloke/Garrulus-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 udkai_garrulus 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 udkai_garrulus on 8 GB VRAM?
Yes, using the Q4_K_M quantised file which estimates 5.9 GB of VRAM at 8k context.
Does the model support vision tasks?
No, the model has no vision capability.
What license applies to this model?
The model is released under the apache-2.0 license.