Downloads · 30 days
208
66% of all-time downloads
GLM-5.3-DERISKED-NVFP4-V2
Blackfrost-Research/GLM-5.3-DERISKED-NVFP4-V2
GLM-5.3-DERISKED-NVFP4-V2 is a text generation model from Blackfrost-Research. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Free public download: Blackfrost-Research/GLM-5.3-DERISKED-NVFP4-V2. No payment, sign-in, or access request is required to download the weights. Existing repository and upstream license terms still apply.
All-time downloads
316
Public
Parameters
391B
465 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors465 GB · 100%
Parameter types
How the weights are stored.
U8362B · 93%
Try a prompt
Base models
Model card
From the Hugging Face model README
Free public download: Blackfrost-Research/GLM-5.3-DERISKED-NVFP4-V2. No payment, sign-in, or access request is required to download the weights. Existing repository and upstream license terms still apply.
GLM-5.3-DERISKED-NVFP4-V2
Deployment-focused ModelOpt NVFP4 derivative of the full GLM-5.3 Mixture-of-Experts model for NVIDIA Blackwell. It retains the complete expert topology and native tokenizer, chat template, reasoning, tool-use, long-context, and MTP metadata.
This is a free, public, ungated release. Blackfrost's weight-level production process is proprietary and is not distributed in this repository.
Specifications
| Architecture | GlmMoeDsaForCausalLM |
| Precision | ModelOpt routed-expert W4A4 NVFP4 mixed precision |
| Layers | 78 main layers plus the native MTP layer |
| Experts | 256 routed experts, top-8 active, plus shared expert |
| Hidden size | 6,144 |
| Context ceiling | 1,048,576 positions |
| Source | zai-org/GLM-5.3-BF16 |
| Target hardware | NVIDIA Blackwell |
DFlash2 deployment
The included deployment kit enables SGLang DFLASH speculative decoding with the
separate revision-pinned incoai/GLM-5.3-DFlash2 companion. Its weights are not
redistributed here. Review the companion's CC BY-NC-ND 4.0 terms before use.
See DEPLOYMENT/README.md and
DEPLOYMENT/LAUNCH.sh.
Qualify the model for your workload before production. Operators remain responsible for access control, monitoring, legal compliance, and treating all model output as untrusted. The model is provided as is, without warranty.
- Task
- Text Generation
- Library
- transformers
- Type
- glm_moe_dsa
- License
- other
- Languages
- en, zh
- Created
- Sep 25, 2026
- Updated
- Oct 11, 2026