Audit Athena quantization inventory and runtime efficiency limits
This commit is contained in:
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"repository": "nvidia/Qwen3.8-27B-NVFP4",
|
||||
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
|
||||
"source": "https://huggingface.co/api/models/nvidia/Qwen3.8-27B-NVFP4?blobs=true",
|
||||
"weight_files": [
|
||||
{
|
||||
"name": "model-00001-of-00003.safetensors",
|
||||
"bytes": 9965652544,
|
||||
"sha256": "7d0fd155118901373eb0fd13ed3aae68f95be747bc205be72ebc41739c25ee80"
|
||||
},
|
||||
{
|
||||
"name": "model-00002-of-00003.safetensors",
|
||||
"bytes": 9985757064,
|
||||
"sha256": "98a7e9486baa860c792c9463a770cb9d017696bdd17606300a5b9334149f4c27"
|
||||
},
|
||||
{
|
||||
"name": "model-00003-of-00003.safetensors",
|
||||
"bytes": 1970287672,
|
||||
"sha256": "0506ad35dc21469708e7813bd76c592cef08bd0317b4a1fe899745ebe2435271"
|
||||
}
|
||||
],
|
||||
"total_weight_bytes": 21921697280,
|
||||
"total_weight_gib": 20.416171550750732,
|
||||
"status": "metadata/capacity review only; not downloaded or benchmarked"
|
||||
}
|
||||
Reference in New Issue
Block a user