SwiftKV reduces prefill compute by up to 50% by combining model rewiring and knowledge-preserving self-distillation.
Snowflake
Enterprise
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
Learn more about our AI research and open source projects, connect with our research team here.
Collections
3
A collection of text embedding models optimized for retrieval accuracy and efficiency
-
Snowflake/snowflake-arctic-embed-m
Sentence Similarity • Updated • 511k • • 151 -
Snowflake/snowflake-arctic-embed-l
Sentence Similarity • Updated • 42.6k • • 91 -
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity • Updated • 25.9k • 34 -
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity • Updated • 269k • 33
models
14
Snowflake/snowflake-arctic-embed-l
Sentence Similarity
•
Updated
•
42.6k
•
•
91
Snowflake/snowflake-arctic-embed-m-v2.0
Sentence Similarity
•
Updated
•
350k
•
60
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity
•
Updated
•
102k
•
•
126
Snowflake/snowflake-arctic-embed-m-v1.5
Sentence Similarity
•
Updated
•
27.5k
•
•
55
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity
•
Updated
•
269k
•
33
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity
•
Updated
•
25.9k
•
34
Snowflake/snowflake-arctic-embed-m
Sentence Similarity
•
Updated
•
511k
•
•
151
Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8
Updated
•
37
Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8
Updated
•
94
Snowflake/Llama-3.1-SwiftKV-8B-Instruct
Updated
•
774
•
7