Mobius Labs GmbH

Team

company

https://www.mobiuslabs.com/

mobiusml

Activity Feed

AI & ML interests

Computer Vision, LLMs, Multimodal Models, Model Compression

Recent Activity

mobicham new activity about 6 hours ago

mobiuslabsgmbh/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit:🙋🏻‍♂️ gemlite hqq quant version "unlearns" tool calling (?)

mobicham new activity about 7 hours ago

mobiuslabsgmbh/Llama-3.1-8B-Instruct_gemlite-ao_a16w4_gs_128_pack_32bit:🙋🏻‍♂️ gemlite hqq quant version "unlearns" tool calling (?)

View all activity

mobiuslabsgmbh 's collections 9

FP4

MXFP4/NVFP4 models

mobiuslabsgmbh/Llama-3.1-8B-Instruct_mxfp4_weights_calib_demo

Text Generation • Updated 29 days ago • 15 • 1
mobiuslabsgmbh/Llama-3.1-8B-Instruct_nvfp4_weights_calib_demo

Text Generation • Updated 29 days ago • 16 • 1

Qwen

HQQ-quantized Qwen models

mobiuslabsgmbh/Qwen2.5-7B-Instruct-1M_4bitgs64_hqq_hf

Text Generation • 5B • Updated Feb 6 • 3 • 1
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct_4bitgs64_hqq_hf

Text Generation • 5B • Updated Apr 23 • 591
mobiuslabsgmbh/Qwen2.5-VL-3B-Instruct_4bitgs64_hqq_hf

Text Generation • 2B • Updated Apr 23 • 3 • 1
mobiuslabsgmbh/Qwen2.5-7B-Instruct_4bitgs64_hqq_hf

Text Generation • 5B • Updated Feb 6 • 3 • 2

Llama3 HQQ

mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib

Text Generation • Updated Feb 5 • 14 • 55
mobiuslabsgmbh/Llama-3.1-8B-Instruct_4bitgs64_hqq_hf

Text Generation • 5B • Updated Feb 6 • 7 • 1
mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq

Text Generation • Updated Feb 5 • 12 • 31
mobiuslabsgmbh/Llama-3.2-3B-Instruct_4bitgs64_hqq_hf

Text Generation • 2B • Updated Feb 6 • 3 • 1

Llama2 HQQ Quantized Models

LLama2 models quantized using https://github.com/mobiusml/hqq

mobiuslabsgmbh/Llama-2-7b-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 4 • 2
mobiuslabsgmbh/Llama-2-13b-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 18 • 1
mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ

Text Generation • Updated Apr 9 • 4 • 2
mobiuslabsgmbh/Llama-2-70b-chat-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 4 • 3

ViT HQQ Quantized Models

ViT models quantized using https://github.com/mobiusml/hqq

mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ

Image Classification • Updated Dec 6, 2023 • 16 • 5

AO/GemLite

Quantized models in AO/GemLite format

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

Text Generation • Updated Jun 3 • 11 • 2
mobiuslabsgmbh/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_32bit

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

Text Generation • Updated Jun 4 • 16 • 2
mobiuslabsgmbh/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit

Text Generation • Updated Jun 4 • 3 • 1

DeepSeek-R1-ReDistill

Re-distilled DeepSeek R1 models

mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1

Text Generation • 8B • Updated Jan 30 • 13 • • 11
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1

Text Generation • 8B • Updated Jan 30 • 10 • 15
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1

Text Generation • 2B • Updated Jan 29 • 66 • 13
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0

Text Generation • 2B • Updated Jan 29 • 26 • 44

Aana

This collection will include language, vision and audio models pre-trained or fine-tuned by Mobius Labs GmbH

mobiuslabsgmbh/aanaphi2-v0.1

Text Generation • 3B • Updated Mar 4, 2024 • 10 • 28

Mixtral HQQ Quantized Models

4-bit and 2-bit Mixtral models quantized using https://github.com/mobiusml/hqq

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 4 • 9
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 11 • 9
mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 6 • 4
mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 5 • 1

FP4

MXFP4/NVFP4 models

mobiuslabsgmbh/Llama-3.1-8B-Instruct_mxfp4_weights_calib_demo

Text Generation • Updated 29 days ago • 15 • 1
mobiuslabsgmbh/Llama-3.1-8B-Instruct_nvfp4_weights_calib_demo

Text Generation • Updated 29 days ago • 16 • 1

AO/GemLite

Quantized models in AO/GemLite format

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

Text Generation • Updated Jun 3 • 11 • 2
mobiuslabsgmbh/Phi-4-mini-instruct_gemlite-ao_a16w4_gs_128_pack_32bit

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

Text Generation • Updated Jun 4 • 16 • 2
mobiuslabsgmbh/Qwen3-32B_gemlite-ao_a16w4_gs_128_pack_32bit

Text Generation • Updated Jun 4 • 3 • 1

Qwen

HQQ-quantized Qwen models

mobiuslabsgmbh/Qwen2.5-7B-Instruct-1M_4bitgs64_hqq_hf

Text Generation • 5B • Updated Feb 6 • 3 • 1
mobiuslabsgmbh/Qwen2.5-VL-7B-Instruct_4bitgs64_hqq_hf

Text Generation • 5B • Updated Apr 23 • 591
mobiuslabsgmbh/Qwen2.5-VL-3B-Instruct_4bitgs64_hqq_hf

Text Generation • 2B • Updated Apr 23 • 3 • 1
mobiuslabsgmbh/Qwen2.5-7B-Instruct_4bitgs64_hqq_hf

Text Generation • 5B • Updated Feb 6 • 3 • 2

DeepSeek-R1-ReDistill

Re-distilled DeepSeek R1 models

mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1

Text Generation • 8B • Updated Jan 30 • 13 • • 11
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1

Text Generation • 8B • Updated Jan 30 • 10 • 15
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1

Text Generation • 2B • Updated Jan 29 • 66 • 13
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0

Text Generation • 2B • Updated Jan 29 • 26 • 44

Llama3 HQQ

mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib

Text Generation • Updated Feb 5 • 14 • 55
mobiuslabsgmbh/Llama-3.1-8B-Instruct_4bitgs64_hqq_hf

Text Generation • 5B • Updated Feb 6 • 7 • 1
mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq

Text Generation • Updated Feb 5 • 12 • 31
mobiuslabsgmbh/Llama-3.2-3B-Instruct_4bitgs64_hqq_hf

Text Generation • 2B • Updated Feb 6 • 3 • 1

Aana

This collection will include language, vision and audio models pre-trained or fine-tuned by Mobius Labs GmbH

mobiuslabsgmbh/aanaphi2-v0.1

Text Generation • 3B • Updated Mar 4, 2024 • 10 • 28

Llama2 HQQ Quantized Models

LLama2 models quantized using https://github.com/mobiusml/hqq

mobiuslabsgmbh/Llama-2-7b-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 4 • 2
mobiuslabsgmbh/Llama-2-13b-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 18 • 1
mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ

Text Generation • Updated Apr 9 • 4 • 2
mobiuslabsgmbh/Llama-2-70b-chat-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 4 • 3

Mixtral HQQ Quantized Models

4-bit and 2-bit Mixtral models quantized using https://github.com/mobiusml/hqq

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 4 • 9
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 11 • 9
mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 6 • 4
mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 5 • 1

ViT HQQ Quantized Models

ViT models quantized using https://github.com/mobiusml/hqq

mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ

Image Classification • Updated Dec 6, 2023 • 16 • 5

AI & ML interests

Recent Activity

Team members 5

mobiuslabsgmbh 's collections 9