Mixture-of-Experts Large Language Models with only active 1-2B parameters that can easily run on consumer hardware (16GB RAM)
d0
d0zz0d
P(doom) <0.001%
AI & ML interests
None yet
Recent Activity
updated a collection about 8 hours ago
Sub-5b T2T LLMs - Finetunes liked a model 1 day ago
SkyIsNotGreen/Scion-35B-A3B liked a model 3 days ago
google/gemma-4-E2B-itOrganizations
None yet
4b is the new 7b, now multimodal!
A list of text-to-text LLMs under 2B parameters, suitable for low-end consumer hardware
A list of Finetuned LLMs, improving some or all aspects of a base LLM
4b is the new 7b, i was meant to do sub-3b and sub-4b collections, but in the end i decided to combine into a single collection of text-to-text LLMs
-
Qwen/Qwen3-4B-Instruct-2507
Text Generation • 4B • Updated • 3.64M • • 993 -
Qwen/Qwen3-4B-Thinking-2507
Text Generation • 4B • Updated • 568k • • 619 -
tencent/Hunyuan-4B-Instruct
Text Generation • 4B • Updated • 729 • 30 -
nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
Text Generation • 4B • Updated • 2.57M • 128
A list of small Image-Text-to-Text Vision Language models, within the sub-2b parameter range.
Lists some sub-1b parameter text-to-text small language models, perfect for edge use, smartphones, or generally weak hardware for below 2GB of RAM.
-
tiiuae/Falcon-H1-Tiny-90M-Instruct
Text Generation • 91.1M • Updated • 1.32k • 48 -
tiiuae/Falcon-H1-Tiny-R-90M
Text Generation • 91.1M • Updated • 504 • 27 -
tiiuae/Falcon-H1-Tiny-Multilingual-100M-Instruct
Text Generation • 0.1B • Updated • 1.23k • 13 -
HuggingFaceTB/SmolLM2-135M-Instruct
Text Generation • 0.1B • Updated • 1.8M • 432
Mixture-of-Experts Large Language Models with only active 1-2B parameters that can easily run on consumer hardware (16GB RAM)
4b is the new 7b, i was meant to do sub-3b and sub-4b collections, but in the end i decided to combine into a single collection of text-to-text LLMs
-
Qwen/Qwen3-4B-Instruct-2507
Text Generation • 4B • Updated • 3.64M • • 993 -
Qwen/Qwen3-4B-Thinking-2507
Text Generation • 4B • Updated • 568k • • 619 -
tencent/Hunyuan-4B-Instruct
Text Generation • 4B • Updated • 729 • 30 -
nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
Text Generation • 4B • Updated • 2.57M • 128
4b is the new 7b, now multimodal!
A list of text-to-text LLMs under 2B parameters, suitable for low-end consumer hardware
A list of small Image-Text-to-Text Vision Language models, within the sub-2b parameter range.
A list of Finetuned LLMs, improving some or all aspects of a base LLM
Lists some sub-1b parameter text-to-text small language models, perfect for edge use, smartphones, or generally weak hardware for below 2GB of RAM.
-
tiiuae/Falcon-H1-Tiny-90M-Instruct
Text Generation • 91.1M • Updated • 1.32k • 48 -
tiiuae/Falcon-H1-Tiny-R-90M
Text Generation • 91.1M • Updated • 504 • 27 -
tiiuae/Falcon-H1-Tiny-Multilingual-100M-Instruct
Text Generation • 0.1B • Updated • 1.23k • 13 -
HuggingFaceTB/SmolLM2-135M-Instruct
Text Generation • 0.1B • Updated • 1.8M • 432