CoreML LLMs optimized for Apple Neural Engine.
Stephen
smpanaro
AI & ML interests
Apple Neural Engine, Quantization
Recent Activity
updated
a model
30 days ago
smpanaro/Qwen2.5-0.5B-4bit-PerTensor
published
a model
about 1 month ago
smpanaro/Qwen2.5-0.5B-4bit-PerTensor
new activity
3 months ago
smpanaro/Llama-3.2-1B-Instruct-CoreML:Context length
Organizations
models
19
smpanaro/Qwen2.5-0.5B-4bit-PerTensor
0.6B
•
Updated
•
389
•
1
smpanaro/Llama3.1-8B-Instruct-LeanQuant-kmeans1d
Updated
smpanaro/Llama-3.2-3B-Instruct-CoreML
Updated
•
4
smpanaro/Llama-3.2-1B-Instruct-CoreML
Updated
•
8
smpanaro/Llama-2-7b-coreml
Updated
•
3
smpanaro/Llama-2-7b-NuGPTQ
Text Generation
•
7B
•
Updated
•
17
•
1
smpanaro/coreml-joint-compression-test
Updated
•
7
smpanaro/whisperkit-coreml
Updated
•
1
smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g
Text Generation
•
Updated
•
15
smpanaro/pythia-70m-AutoGPTQ-4bit-128g
Text Generation
•
Updated
•
11
datasets
0
None public yet