MXFP4/NVFP4 models
AI & ML interests
Computer Vision, LLMs, Multimodal Models, Model Compression
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
-
dropbox-dash/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 53 • 2 -
dropbox-dash/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 104 • 1 -
dropbox-dash/Qwen2.5-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 54 • 2 -
dropbox-dash/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 54 • 1
MXFP4/NVFP4 models
Quantized models in AO/GemLite format
-
dropbox-dash/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 53 • 2 -
dropbox-dash/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 104 • 1 -
dropbox-dash/Qwen2.5-7B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 54 • 2 -
dropbox-dash/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit
Text Generation • Updated • 54 • 1
models
28
mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ
Image Classification
•
Updated
•
37
•
5
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct-leftpad
Updated
mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ
Text Generation
•
Updated
•
67
•
2
mobiuslabsgmbh/gemma-3-12b-it_4bitgs64_bfp16_hqq_hf
8B
•
Updated
•
37
•
2
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1_4bitgs64_hqq_hf
Text Generation
•
25B
•
Updated
•
32
•
1
mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq
Text Generation
•
Updated
•
72
•
74
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ
Text Generation
•
Updated
•
29
•
19
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ
Text Generation
•
Updated
•
32
•
16
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-3bit-metaoffload-HQQ
Text Generation
•
Updated
•
34
•
13
mobiuslabsgmbh/Llama-2-7b-chat-hf-4bit_g64-HQQ
Text Generation
•
Updated
•
32
•
3