Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
sapidlabs
/
Sparkulator-GLM-5.2
like
4
Follow
Sapid Labs
7
Text Generation
Safetensors
speculators
speculative-decoding
dspark
compressed-tensors
w4a16
dgx-spark
custom_code
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Sparkulator-GLM-5.2
4.91 GB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
jtmuller
W4A16 quantized dspark speculator for GLM-5.2 on DGX Spark (+8.7% decode, no acceptance cost)
ea21715
verified
15 days ago
.gitattributes
Safe
1.52 kB
initial commit
15 days ago
README.md
Safe
6.63 kB
W4A16 quantized dspark speculator for GLM-5.2 on DGX Spark (+8.7% decode, no acceptance cost)
15 days ago
config.json
Safe
2.67 kB
W4A16 quantized dspark speculator for GLM-5.2 on DGX Spark (+8.7% decode, no acceptance cost)
15 days ago
config.py
Safe
1.88 kB
W4A16 quantized dspark speculator for GLM-5.2 on DGX Spark (+8.7% decode, no acceptance cost)
15 days ago
model.safetensors
4.91 GB
xet
W4A16 quantized dspark speculator for GLM-5.2 on DGX Spark (+8.7% decode, no acceptance cost)
15 days ago
