Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
apolo13x
/
Qwen3.5-27B-NVFP4
like
39
Image-Text-to-Text
Transformers
Safetensors
neuralmagic/calibration
qwen3_5
quantized
nvfp4
fp4
4-bit precision
vllm
llm-compressor
conversational
8-bit precision
compressed-tensors
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
4
Deploy
Use this model
Does this model have MTP layers?
#2
by
unoid
- opened
Mar 14
Discussion
unoid
Mar 14
title, MTP enabled? Any divergence or KLD tests versus fp8 or 16bit?
See translation
π
2
2
+
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Comment
Β·
Sign up
or
log in
to comment