Qwen3.8-2.4T-A95B-NVFP4
95B open-weight LLM by nvidia
Live
Open / InstallLast updated October 23, 2026
Description
Qwen3.8-2.4T-A95B-NVFP4 is an open-weight text-generation model with roughly 95B parameters published by nvidia on the Hugging Face Hub. It has 10,813 downloads. Runs with Model Optimizer.
Community Metrics
Views
23
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
nvidia
Platform
api
Pricing model
free
Categories
- Productivity
Tags
- Model Optimizer
- qwen3_5_moe_text
- NVIDIA
- ModelOpt
- Qwen3.8
- quantized
- 4-bit precision
- FP4
Capabilities
- Text generation
- Conversational
- Library: Model Optimizer
- 95B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 6, 2026