GLM-5.3-Flash-BF16
Z.ai- 321.3B parameters
- Mixture of experts, 18B active
- MIT
- Released in bf16
- Estimated
zai-org/GLM-5.3-Flash-BF16 on Hugging Face
GLM-5.3-Flash-BF16 with Glyd
| bf16 | Glyd | Change, % | ||
|---|---|---|---|---|
| Weights in GPU memory, GBEstimated from the parameter count | 642.65 | 432.51est. | −33 | |
| 8×H100 nodes it takesWeights and an 8K-token KV cache | 1 | 1 | ||
| H100 80 GB GPUs it takes | 8 | 6 |
Which single GPU it fits
Estimated from the parameter count.
| Memory | GPUs | bf16 | Glyd |
|---|---|---|---|
| 16 GB | RTX 4080, RTX 5080 | No | No |
| 24 GB | RTX 4090, RTX 3090, A10 | No | No |
| 32 GB | RTX 5090 | No | No |
| 48 GB | RTX A6000, L40S, RTX 6000 Ada | No | No |
| 80 GB | H100, A100 80 GB | No | No |
| 96 GB | RTX PRO 6000, GH200 | No | No |
| 141 GB | H200 | No | No |
Related models
Measured so far
Twenty-two open models measured, with quality wherever bf16 fits one GPU.