GGUF importance matrix (imatrix) quants for https://huggingface.co/wolfram/miquliz-120b-v2.0
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Using IQ2_XXS it seems to fit 100/141 layers using 2K context on a 24GB card.

Layers	Context	Template
140	32768	[INST] {prompt} [/INST] {response}

Downloads last month: 25

GGUF

Model size

120B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support