Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
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
Avifenesh
/
GLM-5.3-Flash-NVFP4
Like
1
Text Generation
Safetensors
English
Chinese
glm5_next
nvfp4
fp4
4-bit precision
modelopt
w4a16
quantized
Mixture of Experts
blackwell
conversational
tool-calling
8-bit precision
arxiv:
2602.15763
License:
mit
Model card
Files
Files and versions
xet
Community
4
Copy to bucket
Context section correction
#2
by
Avifenesh
- opened
Aug 30
base:
refs/heads/main
←
from:
refs/pr/2
Discussion
Files changed
+2936
-0
Model card: NVFP4 mint of GLM-5.3-Flash, gated against its BF16 source
b472f99f
initial commit
efe10afc
Config, tokenizer, chat template, quant config
58df4696
NVFP4 weights, 20 shards
25346cae
Card: add the 4-bit facet; the auto-detected 8-bit tag reads the FP8 scale plane, not the weights
f66141cd
Context: state the vendor 1M figure as the vendors, and show where our practical wall is
a8937d13
Avifenesh
Owner
Aug 30
Hugging Face CLI
No description provided.
Context section correction
e4defa8d
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Cannot merge
This branch has merge conflicts in the following files:
README.md
Comment
·
Sign up
or
log in
to comment