Llamacpp imatrix Quantizations of Llama-3.1-70B-ArliAI-RPMax-v1.3

Using llama.cpp release b4132 for quantization.

Original model: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3

All quants made using imatrix option with dataset from here

Run them in LM Studio

Prompt format

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

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

Q4_0_X_X information

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:

Which file should I choose?

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

Base model

ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3

(5)

This collection contains some of the recent models larger than ~25B parameters that should be high quality and reliable • 15 items • Updated Nov 27, 2024 • 62