Sponsored by Tripo AI
Toolify Toolify logo
AI Models
Perciqa_Aurora-Code-1-GGUF

bartowski / Perciqa_Aurora-Code-1-GGUF

Run on huggingface.co
huggingface.co
Total runs: 1.6K
24-hour runs: -257
7-day runs: -361
30-day runs: -2.3K
Model's Last Updated: July 20 2026
text-generation

Introduction of Perciqa_Aurora-Code-1-GGUF

Model Details of Perciqa_Aurora-Code-1-GGUF

Llamacpp imatrix Quantizations of Aurora-Code-1 by Perciqa

Using llama.cpp release b10068 for quantization.

Original model: https://huggingface.co/Perciqa/Aurora-Code-1

All quants made using imatrix option with dataset from here

Run them in your choice of tools:

Note: if it's a newly supported model, you may need to wait for an update from the developers.

Prompt format 
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>
Download a file (not the whole branch) from below:
Filename Quant type File Size Split Description
Perciqa_Aurora-Code-1-bf16.gguf bf16 69.38GB true Full BF16 weights.
Perciqa_Aurora-Code-1-Q8_0.gguf Q8_0 36.91GB false Extremely high quality, generally unneeded but max available quant.
Perciqa_Aurora-Code-1-Q6_K_L.gguf Q6_K_L 30.30GB false Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended .
Perciqa_Aurora-Code-1-Q6_K.gguf Q6_K 30.05GB false Very high quality, near perfect, recommended .
Perciqa_Aurora-Code-1-Q5_K_L.gguf Q5_K_L 25.33GB false Uses Q8_0 for embed and output weights. High quality, recommended .
Perciqa_Aurora-Code-1-Q5_K_M.gguf Q5_K_M 25.02GB false High quality, recommended .
Perciqa_Aurora-Code-1-Q5_K_S.gguf Q5_K_S 24.16GB false High quality, recommended .
Perciqa_Aurora-Code-1-Q4_1.gguf Q4_1 21.97GB false Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
Perciqa_Aurora-Code-1-Q4_K_L.gguf Q4_K_L 21.77GB false Uses Q8_0 for embed and output weights. Good quality, recommended .
Perciqa_Aurora-Code-1-Q4_K_M.gguf Q4_K_M 21.39GB false Good quality, default size for most use cases, recommended .
Perciqa_Aurora-Code-1-Q4_K_S.gguf Q4_K_S 20.59GB false Slightly lower quality with more space savings, recommended .
Perciqa_Aurora-Code-1-Q4_0.gguf Q4_0 19.94GB false Legacy format, offers online repacking for ARM and AVX CPU inference.
Perciqa_Aurora-Code-1-IQ4_NL.gguf IQ4_NL 19.86GB false Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference.
Perciqa_Aurora-Code-1-IQ4_XS.gguf IQ4_XS 18.81GB false Decent quality, smaller than Q4_K_S with similar performance, recommended .
Perciqa_Aurora-Code-1-Q3_K_XL.gguf Q3_K_XL 17.33GB false Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
Perciqa_Aurora-Code-1-IQ3_M.gguf IQ3_M 16.90GB false Medium-low quality, new method with decent performance comparable to Q3_K_M.
Perciqa_Aurora-Code-1-Q3_K_L.gguf Q3_K_L 16.89GB false Lower quality but usable, good for low RAM availability.
Perciqa_Aurora-Code-1-Q3_K_M.gguf Q3_K_M 16.23GB false Low quality.
Perciqa_Aurora-Code-1-IQ3_XS.gguf IQ3_XS 16.22GB false Lower quality, new method with decent performance, slightly better than Q3_K_S.
Perciqa_Aurora-Code-1-Q3_K_S.gguf Q3_K_S 15.51GB false Low quality, not recommended.
Perciqa_Aurora-Code-1-IQ3_XXS.gguf IQ3_XXS 14.87GB false Lower quality, new method with decent performance, comparable to Q3 quants.
Perciqa_Aurora-Code-1-Q2_K_L.gguf Q2_K_L 13.11GB false Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
Perciqa_Aurora-Code-1-Q2_K.gguf Q2_K 12.62GB false Very low quality but surprisingly usable.
Perciqa_Aurora-Code-1-IQ2_M.gguf IQ2_M 12.07GB false Relatively low quality, uses SOTA techniques to be surprisingly usable.
Perciqa_Aurora-Code-1-IQ2_S.gguf IQ2_S 11.01GB false Low quality, uses SOTA techniques to be usable.
Perciqa_Aurora-Code-1-IQ2_XS.gguf IQ2_XS 10.80GB false Low quality, uses SOTA techniques to be usable.
Perciqa_Aurora-Code-1-IQ2_XXS.gguf IQ2_XXS 9.78GB false Very low quality, uses SOTA techniques to be usable.
Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli
Click to view download instructions

First, make sure you have huggingface-cli installed: 

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want: 

huggingface-cli download bartowski/Perciqa_Aurora-Code-1-GGUF --include "Perciqa_Aurora-Code-1-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: 

huggingface-cli download bartowski/Perciqa_Aurora-Code-1-GGUF --include "Perciqa_Aurora-Code-1-Q8_0/*" --local-dir ./

You can either specify a new local-dir (Perciqa_Aurora-Code-1-Q8_0) or download them all in place (./)

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR . If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality, you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed increase.

Click to view Q4_0_X_X information (deprecated)

I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.

Click to view benchmarks on an AVX2 system (EPYC7702)
model size params backend threads test t/s % (vs Q4_0)
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 pp512 204.03 ± 1.03 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 pp1024 282.92 ± 0.19 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 pp2048 259.49 ± 0.44 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 tg128 39.12 ± 0.27 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 tg256 39.31 ± 0.69 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 tg512 40.52 ± 0.03 100%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 pp512 301.02 ± 1.74 147%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 pp1024 287.23 ± 0.20 101%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 pp2048 262.77 ± 1.81 101%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 tg128 18.80 ± 0.99 48%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 tg256 24.46 ± 3.04 83%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 tg512 36.32 ± 3.59 90%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 pp512 271.71 ± 3.53 133%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 pp1024 279.86 ± 45.63 100%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 pp2048 320.77 ± 5.00 124%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 tg128 43.51 ± 0.05 111%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 tg256 43.35 ± 0.09 110%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 tg512 42.60 ± 0.31 105%

Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation

Which file should I choose?
Click here for details

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Runs of bartowski Perciqa_Aurora-Code-1-GGUF on huggingface.co

1.6K
Total runs
-257
24-hour runs
-368
3-day runs
-361
7-day runs
-2.3K
30-day runs

More Information About Perciqa_Aurora-Code-1-GGUF huggingface.co Model

More Perciqa_Aurora-Code-1-GGUF license Visit here:

https://choosealicense.com/licenses/apache-2.0

Perciqa_Aurora-Code-1-GGUF huggingface.co

Perciqa_Aurora-Code-1-GGUF huggingface.co is an AI model on huggingface.co that provides Perciqa_Aurora-Code-1-GGUF's model effect (), which can be used instantly with this bartowski Perciqa_Aurora-Code-1-GGUF model. huggingface.co supports a free trial of the Perciqa_Aurora-Code-1-GGUF model, and also provides paid use of the Perciqa_Aurora-Code-1-GGUF. Support call Perciqa_Aurora-Code-1-GGUF model through api, including Node.js, Python, http.

Perciqa_Aurora-Code-1-GGUF huggingface.co Url

https://huggingface.co/bartowski/Perciqa_Aurora-Code-1-GGUF

bartowski Perciqa_Aurora-Code-1-GGUF online free

Perciqa_Aurora-Code-1-GGUF huggingface.co is an online trial and call api platform, which integrates Perciqa_Aurora-Code-1-GGUF's modeling effects, including api services, and provides a free online trial of Perciqa_Aurora-Code-1-GGUF, you can try Perciqa_Aurora-Code-1-GGUF online for free by clicking the link below.

bartowski Perciqa_Aurora-Code-1-GGUF online free url in huggingface.co:

https://huggingface.co/bartowski/Perciqa_Aurora-Code-1-GGUF

Perciqa_Aurora-Code-1-GGUF install

Perciqa_Aurora-Code-1-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Perciqa_Aurora-Code-1-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Perciqa_Aurora-Code-1-GGUF install, users can directly use Perciqa_Aurora-Code-1-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Perciqa_Aurora-Code-1-GGUF install url in huggingface.co:

https://huggingface.co/bartowski/Perciqa_Aurora-Code-1-GGUF

Url of Perciqa_Aurora-Code-1-GGUF

Perciqa_Aurora-Code-1-GGUF huggingface.co Url

Provider of Perciqa_Aurora-Code-1-GGUF huggingface.co

bartowski
ORGANIZATIONS
huggingface.co

Other API from bartowski

 huggingface.co
bartowski/Hy3-GGUF

Total runs: 42.1K
Run Growth: -5.2K
Growth Rate: -12.29%
Updated:July 15 2026