nvidia
/

GLM-5.3-Flash-FP4-Local

Image-Text-to-Text

Model Optimizer

8-bit precision

Model card Files Files and versions

Update README.md

#5

by MackenzieNVIDIA - opened 2 days ago

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -20,8 +20,8 @@ tags:
 The NVIDIA GLM-5.3-Flash-FP4-Local model is the quantized version of ZAI's GLM-5.3-Flash model, which is an auto-regressive language model that uses an optimized transformer architecture. GLM-5.3-Flash is a natively multimodal Mixture-of-Experts (MoE) model for reasoning, coding, and agentic tasks; it uses a hybrid sparse and linear attention architecture with Manifold-Constrained Hyper-Connections (mHC) to support a long context. For more information, please check [here](https://huggingface.co/zai-org/GLM-5.3-Flash). The NVIDIA GLM-5.3-Flash-FP4-Local model is quantized with [Model Optimizer](https://github.com/NVIDIA/Model-Optimizer) using [quantization-aware distillation (QAD)](https://developer.nvidia.com/blog/how-quantization-aware-training-enables-low-precision-accuracy-recovery/).
 This checkpoint is best suited for local AI hardware and uses approximately **166 GiB of vRAM**. It has been validated with vLLM on the following hardware: <br>
-* **NVIDIA RTX PRO 6000 Blackwell** <br>
-* **NVIDIA DGX Spark** <br>
 This model is ready for commercial or non-commercial use.  <br>

 The NVIDIA GLM-5.3-Flash-FP4-Local model is the quantized version of ZAI's GLM-5.3-Flash model, which is an auto-regressive language model that uses an optimized transformer architecture. GLM-5.3-Flash is a natively multimodal Mixture-of-Experts (MoE) model for reasoning, coding, and agentic tasks; it uses a hybrid sparse and linear attention architecture with Manifold-Constrained Hyper-Connections (mHC) to support a long context. For more information, please check [here](https://huggingface.co/zai-org/GLM-5.3-Flash). The NVIDIA GLM-5.3-Flash-FP4-Local model is quantized with [Model Optimizer](https://github.com/NVIDIA/Model-Optimizer) using [quantization-aware distillation (QAD)](https://developer.nvidia.com/blog/how-quantization-aware-training-enables-low-precision-accuracy-recovery/).
 This checkpoint is best suited for local AI hardware and uses approximately **166 GiB of vRAM**. It has been validated with vLLM on the following hardware: <br>
+* **2 x NVIDIA RTX PRO 6000 Blackwell with 1.8M tokens of FP8 KV Cache ** <br>
+* **2 x NVIDIA DGX Spark 128 GB with 2M tokens of FP8 KV Cache ** <br>
 This model is ready for commercial or non-commercial use.  <br>