MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
Paper • 2402.14905 • Published • 134
MobileLLM
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905
-
-
facebook/MobileLLM-125M
Text Generation • Updated • 984 • 130 -
facebook/MobileLLM-350M
Text Generation • Updated • 62 • 36 -
facebook/MobileLLM-600M
Text Generation • Updated • 54 • 29 -
facebook/MobileLLM-1B
Text Generation • Updated • 122 • 122 -
facebook/MobileLLM-1.5B
Text Generation • Updated • 2 • 13 -
facebook/MobileLLM-125M-layer-share
Text Generation • Updated • 8 -
facebook/MobileLLM-350M-layer-share
Text Generation • Updated • 7 -
ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization
Paper • 2502.02631 • Published • 4 -
facebook/MobileLLM-ParetoQ-125M-BF16
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-125M-1-bit
Text Generation • Updated • 1 -
facebook/MobileLLM-ParetoQ-125M-1.58-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-125M-2-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-125M-3-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-125M-4-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-350M-BF16
Text Generation • Updated • 3 -
facebook/MobileLLM-ParetoQ-350M-1-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-350M-1.58-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-350M-2-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-350M-3-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-350M-4-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-600M-BF16
Text Generation • Updated • 7 -
facebook/MobileLLM-ParetoQ-600M-1-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-600M-1.58-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-600M-2-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-600M-3-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-600M-4-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1B-BF16
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1B-1-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1B-1.58-bit
Text Generation • Updated • 1 -
facebook/MobileLLM-ParetoQ-1B-2-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1B-3-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1B-4-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1.5B-BF16
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1.5B-1-bit
Text Generation • Updated • 13 -
facebook/MobileLLM-ParetoQ-1.5B-1.58-bit
Text Generation • Updated • 100 -
facebook/MobileLLM-ParetoQ-1.5B-2-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1.5B-3-bit
Text Generation • Updated -
facebook/MobileLLM-ParetoQ-1.5B-4-bit
Text Generation • Updated • 2 -
MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
Paper • 2509.24945 • Published • 5 -
facebook/MobileLLM-R1.5-950M
Text Generation • 0.9B • Updated • 56 • 19 -
facebook/MobileLLM-R1.5-360M
Text Generation • 0.4B • Updated • 100 • 8 -
facebook/MobileLLM-R1.5-140M
Text Generation • 0.1B • Updated • 66 • 9 -
facebook/MobileLLM-R1-950M
Text Generation • 0.9B • Updated • 1.19k • 281 -
facebook/MobileLLM-R1-950M-base
Text Generation • 0.9B • Updated • 83 • 19 -
facebook/MobileLLM-R1-360M
Text Generation • 0.4B • Updated • 27 • 22 -
facebook/MobileLLM-R1-360M-base
Text Generation • 0.4B • Updated • 9 • 12 -
facebook/MobileLLM-R1-140M
Text Generation • 0.1B • Updated • 153 • 37 -
facebook/MobileLLM-R1-140M-base
Text Generation • 0.1B • Updated • 17