Using llama.cpp b4682 (commit 0893e0114e934bdd0eba0ff69d9ef8c59343cbc3)

The importance matrix was generated with groups_merged-enhancedV3.txt by InferenceIllusionist (later renamed calibration_datav3.txt), an edited version of kalomaze's original groups_merged.txt.

All quants were generated/calibrated with the imatrix, including the K quants.

Downloads last month: 1,292

GGUF

Model size

72.7B params

Architecture

qwen2

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

View +3 variants

Inference Providers NEW

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

Model tree for redponike/AceMath-72B-Instruct-GGUF

Base model

Qwen/Qwen2.5-72B

Finetuned

Qwen/Qwen2.5-Math-72B

Quantized

(7)

this model