OLMo-2-1124-7B-Instruct-GGUF

Llamacpp imatrix Quantizations of OLMo-2-1124-7B-Instruct

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4191">b4191</a> for quantization.

Original model: https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct

All quants made using imatrix option with dataset from here

These were made by fixing the tokenizer.json pre_processor, using the one from the base model.

Prompt format

<|endoftext|><|system|>
{system_prompt}
<|user|>
{prompt}
<|assistant|>

Download a file (not the whole branch) from below:

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

<details> <summary>Click to view download instructions</summary>

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/OLMo-2-1124-7B-Instruct-GGUF --include "OLMo-2-1124-7B-Instruct-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/OLMo-2-1124-7B-Instruct-GGUF --include "OLMo-2-1124-7B-Instruct-Q8_0/*" --local-dir ./

You can either specify a new local-dir (OLMo-2-1124-7B-Instruct-Q8_0) or download them all in place (./)

</details>

Q4_0_X_X information

<details> <summary>Click to view Q4_0_X_X information</summary> These are *NOT* for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).

If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons on the original pull request

To check which one would work best for your ARM chip, you can check AArch64 SoC features (thanks EloyOn!).

If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:

<details> <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>

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

</details> </details>

Which file should I choose?

<details> <summary>Click here for details</summary>

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.

</details>

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