AO/GemLite - a mobiuslabsgmbh Collection

mobiuslabsgmbh 's Collections

FP4

Qwen

DeepSeek-R1-ReDistill

Aana

Llama2 HQQ Quantized Models

Mixtral HQQ Quantized Models

ViT HQQ Quantized Models

AO/GemLite

updated Jun 6

Quantized models in AO/GemLite format

mobiuslabsgmbh/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit

Text Generation • Updated Jun 3 • 10 • 1
mobiuslabsgmbh/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_32bit

Text Generation • Updated Jun 4 • 1
mobiuslabsgmbh/Qwen2.5-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit

Text Generation • Updated Jun 4 • 20 • 2
mobiuslabsgmbh/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit

Text Generation • Updated Jun 4 • 2 • 1
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct_gemlite-ao_a8w8

Image-to-Text • Updated Jun 6 • 34 • 2
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit

Image-to-Text • Updated Jun 4 • 6 • 1
mobiuslabsgmbh/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_16bit

Text Generation • Updated Jun 4 • 1 • 1
mobiuslabsgmbh/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_16bit

Text Generation • Updated Jun 4 • 5 • 1