Hugging Face's logo

Ex0bit
/
Qwen3-VLTO-32B-Instruct-NVFP4-256K

Text Generation
Safetensors
English
qwen3
quantization
nvfp4
nvidia
dgx-spark
blackwell
model_hub_mixin
pytorch_model_hub_mixin
conversational
8-bit precision
modelopt
Model card Files
xet
Community
Qwen3-VLTO-32B-Instruct-NVFP4-256K / chat_template.jinja

Commit History

Upload NVFP4-quantized Qwen3-VLTO-32B with 256K context (YaRN RoPE scaling)
f64de72
verified

Ex0bit commited on