Loading…
Loading…
Models / GLM-5.3-Flash-BF16
1 model (~321B) · ↓ 251.3K downloads a month · from $4.73/h on 8x RTX 5090 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalzai-org/GLM-5.3-Flash-BF16 | vLLM | 643 GB | 723 GB | $11.77/h 8x RTX PRO 6000 |
| GLM 5.3 Flash NVFP4 (RadixArk)RadixArk/GLM-5.3-Flash-NVFP4 | vLLM | 203 GB | 234.4 GB | $4.73/h 8x RTX 5090 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").