Downloads · 30 days
30
14% of all-time downloads
festr2/glm51-nvfp4-w4a16-fp8pbwo-l45-47-l51-62-20260517
glm51-nvfp4-w4a16-fp8pbwo-l45-47-l51-62-20260517 is a machine learning model from festr2. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
GLM-5.1 mixed precision checkpoint for vLLM experiments.
Downloads · 30 days
30
14% of all-time downloads
All-time downloads
216
Public
Parameters
500B
551 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors529 GB · 100%
How the weights are stored.
U8290B · 58%
From the Hugging Face model README
GLM-5.1 mixed precision checkpoint for vLLM experiments.
lukealonso/GLM-5.1-NVFP4FP8_PB_WO)
tensors from zai-org/GLM-5.1-FP8.45-47,51-62config.json: modelopt / MIXED_PRECISIONB12X_MOE_FORCE_A16=1)Validation summary against FP8 reference logits:
| windows | KLD |
|---|---|
| 8 | 0.044499 |
| 42 | 0.054121 |
Runtime footprint observed in vLLM KLD runner:
| model memory / rank | KV cache tokens |
|---|---|
| 46.77 GiB | 654080 |
Canonical vLLM support commit:
61eac2779 Support ModelOpt mixed FP8_PB_WO MoE