MXFP4/NVFP4 models
AI & ML interests
Computer Vision, LLMs, Multimodal Models, Model Compression
Recent Activity
View all activity
Organization Card
Multimodal AI on a global scale. Advocates for Open Source and Open Intelligence. Currently investigating how to make Large Machine Learning Models smaller and democratize them for GPU-poor environments. Visit https://mobiusml.github.io/blog/ to see some of our recent work.
Quantized models in AO/GemLite format
-
mobiuslabsgmbh/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 20 • 2 -
mobiuslabsgmbh/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 23 • 1 -
mobiuslabsgmbh/Qwen2.5-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 13 • 2 -
mobiuslabsgmbh/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 22 • 1
MXFP4/NVFP4 models
Quantized models in AO/GemLite format
-
mobiuslabsgmbh/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 20 • 2 -
mobiuslabsgmbh/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 23 • 1 -
mobiuslabsgmbh/Qwen2.5-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 13 • 2 -
mobiuslabsgmbh/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 22 • 1
models
52
mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ
Image Classification
•
Updated
•
16
•
5
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct-leftpad
Updated
mobiuslabsgmbh/Llama-3.1-8B-Instruct_mxfp4_weights_calib_demo
Text Generation
•
Updated
•
17
•
1
mobiuslabsgmbh/Llama-3.1-8B-Instruct_nvfp4_weights_calib_demo
Text Generation
•
Updated
•
15
•
1
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct_gemlite-ao_a8w8
Image-to-Text
•
Updated
•
28
•
3
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Image-to-Text
•
Updated
•
11
•
2
mobiuslabsgmbh/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_16bit
Text Generation
•
Updated
•
23
•
1
mobiuslabsgmbh/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_16bit
Text Generation
•
Updated
•
13
•
1
mobiuslabsgmbh/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation
•
Updated
•
22
•
1
mobiuslabsgmbh/Qwen2.5-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation
•
Updated
•
13
•
2