Loading…
Loading…
Models / GLM-5.3-Flash / GLM-5.3-Flash ~321B
Vision + text · served with vLLM · ↓ 87K downloads a month · View on Hugging Face
tattrongvu/GLM-5.3-Flash-NVFP4 needs about 225.2 GB of GPU memory for conversations of up to 8,192 tokens. It runs on 8x RTX 4090 from $4.43/h right now; best value: 4x RTX PRO 6000 at $6.76/h.
The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.
| Version | Runtime | Weights | GPU memory | Cheapest machine now | Deploy |
|---|---|---|---|---|---|
| Originalzai-org/GLM-5.3-Flash | vLLM | 328 GB | 373.8 GB | $6.73/h 4x RTX PRO 6000 | Deploy |
| NVFP4 (tattrongvu)tattrongvu/GLM-5.3-Flash-NVFP4 | vLLM | 195 GB | 225.2 GB | $4.26/h 8x RTX 5090 | |
| NVFP4 (nvidia)nvidia/GLM-5.3-Flash-NVFP4 | vLLM | 204 GB | 236.1 GB | $4.26/h 8x RTX 5090 | Deploy |
| MXFP4 Mixed CT AutoRound (INCModel3)INCModel3/GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound | vLLM | 183 GB | 212.7 GB | $4.26/h 8x RTX 5090 | Deploy |
$6.76/h from your balance while it runs, billed by the hour; stop it from its page. GridPup rents the machine, which downloads the model from Hugging Face (usually ready in 10 to 15 minutes), and gives you an https address, keys and a Playground.
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability of 90% or more that download at 200 Mbit/s or more are offered: the machine fetches the model itself.