Downloads · 30 days
33
13% of all-time downloads
GLM-4.5-Air-NVFP4-KV-cache-FP8
soundsgoodai/GLM-4.5-Air-NVFP4-KV-cache-FP8
GLM-4.5-Air-NVFP4-KV-cache-FP8 is a text generation model from soundsgoodai. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
A quantization setup used for GLM-4.5-Air: - Weights: NVFP4 - KV cache: FP8 - Tooling: NVIDIA/Model-Optimizer
All-time downloads
247
Public
Parameters
54.1B
69.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors69.2 GB · 100%
Parameter types
How the weights are stored.
U852.8B · 82%
Try a prompt
Base models
Model card
From the Hugging Face model README
Model Description
A quantization setup used for GLM-4.5-Air:
- Weights: NVFP4
- KV cache: FP8
- Tooling: NVIDIA/Model-Optimizer
Deploy with TensorRT-LLM
- Task
- Text Generation
- Type
- glm4_moe
- License
- apache-2.0
- Created
- Jan 13, 2026
- Updated
- Jan 13, 2026