Thomas Nguyen
ThomasTheMaker
AI & ML interests
Building the world's fastest CPU LLM inference layer
Recent Activity
updated
a collection
5 days ago
RKLLM-v1.2.0
updated
a model
5 days ago
ThomasTheMaker/Ovis2-1B-RKLLM-1.2.0
published
a model
5 days ago
ThomasTheMaker/Ovis2-1B-RKLLM-1.2.0
Organizations
None yet
A list of my favorite small models
-
bartowski/soob3123_amoral-gemma3-4B-GGUF
Text Generation • 4B • Updated • 368 • 4 -
soob3123/amoral-gemma3-1B-v2-gguf
Text Generation • 1.0B • Updated • 145 • 4 -
bartowski/Dolphin3.0-Llama3.2-3B-GGUF
Text Generation • 3B • Updated • 5.09k • 23 -
bartowski/Dolphin3.0-Llama3.2-1B-GGUF
Text Generation • 1B • Updated • 2.85k • 5
-
MTSAIR/Llama3.1-6B-ReplaceMe-Healed
6B • Updated • 3 • 1 -
ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations
Paper • 2505.02819 • Published • 25 -
ThomasTheMaker/meta-llama_Llama-3.2-1B-Instruct_8_layers_3_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1
0.7B • Updated • 4 -
ThomasTheMaker/Llama3.1-1B-Instruct-4-LayerReplaceMe-1.2.0-rkllm
Updated • 1
List of language models verified to work on RKLLM 1.1.2
-
MTSAIR/Llama3.1-6B-ReplaceMe-Healed
6B • Updated • 3 • 1 -
ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations
Paper • 2505.02819 • Published • 25 -
ThomasTheMaker/meta-llama_Llama-3.2-1B-Instruct_8_layers_3_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1
0.7B • Updated • 4 -
ThomasTheMaker/Llama3.1-1B-Instruct-4-LayerReplaceMe-1.2.0-rkllm
Updated • 1
List of language models verified to work on RKLLM 1.1.2
A list of my favorite small models
-
bartowski/soob3123_amoral-gemma3-4B-GGUF
Text Generation • 4B • Updated • 368 • 4 -
soob3123/amoral-gemma3-1B-v2-gguf
Text Generation • 1.0B • Updated • 145 • 4 -
bartowski/Dolphin3.0-Llama3.2-3B-GGUF
Text Generation • 3B • Updated • 5.09k • 23 -
bartowski/Dolphin3.0-Llama3.2-1B-GGUF
Text Generation • 1B • Updated • 2.85k • 5