Downloads · 30 days
24
12% of all-time downloads
festr2/glm51-nvfp4-w4a16-fp8pbwo-l42-47-l51-62-20260517
glm51-nvfp4-w4a16-fp8pbwo-l42-47-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
24
12% of all-time downloads
All-time downloads
206
Public
Parameters
513B
560 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors542 GB · 100%
How the weights are stored.
U8275B · 54%
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-FP8.42-47,51-62config.json: modelopt / MIXED_PRECISIONB12X_MOE_FORCE_A16=1)Validation summary against FP8 reference logits:
| windows | KLD |
|---|---|
| 8 | 0.043555 |
| 42 | 0.051939 |
Runtime footprint observed in vLLM KLD runner:
| model memory / rank | KV cache tokens |
|---|---|
| 48.25 GiB | 628224 |
Canonical vLLM support commit:
61eac2779 Support ModelOpt mixed FP8_PB_WO MoE