bartowski / Mistral-Nemo-Instruct-2407-GGUF

huggingface.co
Total runs: 21.8K
24-hour runs: -116
7-day runs: 2.1K
30-day runs: 10.5K
Model's Last Updated: Novembre 05 2024
text-generation

Introduction of Mistral-Nemo-Instruct-2407-GGUF

Model Details of Mistral-Nemo-Instruct-2407-GGUF

Llamacpp imatrix Quantizations of Mistral-Nemo-Instruct-2407

Using llama.cpp release b3436 for quantization.

Original model: https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407

All quants made using imatrix option with dataset from here

Run them in LM Studio

Prompt format
<s>[INST] {prompt}[/INST] </s>
Download a file (not the whole branch) from below:
Filename Quant type File Size Split Description
Mistral-Nemo-Instruct-2407-f32.gguf f32 49.00GB false Full F32 weights.
Mistral-Nemo-Instruct-2407-Q8_0.gguf Q8_0 13.02GB false Extremely high quality, generally unneeded but max available quant.
Mistral-Nemo-Instruct-2407-Q6_K_L.gguf Q6_K_L 10.38GB false Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended .
Mistral-Nemo-Instruct-2407-Q6_K.gguf Q6_K 10.06GB false Very high quality, near perfect, recommended .
Mistral-Nemo-Instruct-2407-Q5_K_L.gguf Q5_K_L 9.14GB false Uses Q8_0 for embed and output weights. High quality, recommended .
Mistral-Nemo-Instruct-2407-Q5_K_M.gguf Q5_K_M 8.73GB false High quality, recommended .
Mistral-Nemo-Instruct-2407-Q5_K_S.gguf Q5_K_S 8.52GB false High quality, recommended .
Mistral-Nemo-Instruct-2407-Q4_K_L.gguf Q4_K_L 7.98GB false Uses Q8_0 for embed and output weights. Good quality, recommended .
Mistral-Nemo-Instruct-2407-Q4_K_M.gguf Q4_K_M 7.48GB false Good quality, default size for must use cases, recommended .
Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf Q3_K_XL 7.15GB false Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
Mistral-Nemo-Instruct-2407-Q4_K_S.gguf Q4_K_S 7.12GB false Slightly lower quality with more space savings, recommended .
Mistral-Nemo-Instruct-2407-IQ4_XS.gguf IQ4_XS 6.74GB false Decent quality, smaller than Q4_K_S with similar performance, recommended .
Mistral-Nemo-Instruct-2407-Q3_K_L.gguf Q3_K_L 6.56GB false Lower quality but usable, good for low RAM availability.
Mistral-Nemo-Instruct-2407-Q3_K_M.gguf Q3_K_M 6.08GB false Low quality.
Mistral-Nemo-Instruct-2407-IQ3_M.gguf IQ3_M 5.72GB false Medium-low quality, new method with decent performance comparable to Q3_K_M.
Mistral-Nemo-Instruct-2407-Q3_K_S.gguf Q3_K_S 5.53GB false Low quality, not recommended.
Mistral-Nemo-Instruct-2407-Q2_K_L.gguf Q2_K_L 5.45GB false Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
Mistral-Nemo-Instruct-2407-IQ3_XS.gguf IQ3_XS 5.31GB false Lower quality, new method with decent performance, slightly better than Q3_K_S.
Mistral-Nemo-Instruct-2407-Q2_K.gguf Q2_K 4.79GB false Very low quality but surprisingly usable.
Mistral-Nemo-Instruct-2407-IQ2_M.gguf IQ2_M 4.44GB false Relatively low quality, uses SOTA techniques to be surprisingly usable.
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

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/Mistral-Nemo-Instruct-2407-GGUF --include "Mistral-Nemo-Instruct-2407-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/Mistral-Nemo-Instruct-2407-GGUF --include "Mistral-Nemo-Instruct-2407-Q8_0.gguf/*" --local-dir Mistral-Nemo-Instruct-2407-Q8_0

You can either specify a new local-dir (Mistral-Nemo-Instruct-2407-Q8_0) or download them all in place (./)

Which file should I choose?

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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.

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

Runs of bartowski Mistral-Nemo-Instruct-2407-GGUF on huggingface.co

21.8K
Total runs
-116
24-hour runs
191
3-day runs
2.1K
7-day runs
10.5K
30-day runs

More Information About Mistral-Nemo-Instruct-2407-GGUF huggingface.co Model

More Mistral-Nemo-Instruct-2407-GGUF license Visit here:

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

Mistral-Nemo-Instruct-2407-GGUF huggingface.co

Mistral-Nemo-Instruct-2407-GGUF huggingface.co is an AI model on huggingface.co that provides Mistral-Nemo-Instruct-2407-GGUF's model effect (), which can be used instantly with this bartowski Mistral-Nemo-Instruct-2407-GGUF model. huggingface.co supports a free trial of the Mistral-Nemo-Instruct-2407-GGUF model, and also provides paid use of the Mistral-Nemo-Instruct-2407-GGUF. Support call Mistral-Nemo-Instruct-2407-GGUF model through api, including Node.js, Python, http.

Mistral-Nemo-Instruct-2407-GGUF huggingface.co Url

https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF

bartowski Mistral-Nemo-Instruct-2407-GGUF online free

Mistral-Nemo-Instruct-2407-GGUF huggingface.co is an online trial and call api platform, which integrates Mistral-Nemo-Instruct-2407-GGUF's modeling effects, including api services, and provides a free online trial of Mistral-Nemo-Instruct-2407-GGUF, you can try Mistral-Nemo-Instruct-2407-GGUF online for free by clicking the link below.

bartowski Mistral-Nemo-Instruct-2407-GGUF online free url in huggingface.co:

https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF

Mistral-Nemo-Instruct-2407-GGUF install

Mistral-Nemo-Instruct-2407-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Mistral-Nemo-Instruct-2407-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Mistral-Nemo-Instruct-2407-GGUF install, users can directly use Mistral-Nemo-Instruct-2407-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Mistral-Nemo-Instruct-2407-GGUF install url in huggingface.co:

https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF

Url of Mistral-Nemo-Instruct-2407-GGUF

Mistral-Nemo-Instruct-2407-GGUF huggingface.co Url

Provider of Mistral-Nemo-Instruct-2407-GGUF huggingface.co

bartowski
ORGANIZATIONS

Other API from bartowski

huggingface.co

Total runs: 32.9K
Run Growth: 735
Growth Rate: 2.18%
Updated: Janvier 11 2025