Skip to main content
The Hugging BayGet a model

AI models that run on this device.

Two small chat models run in a computer’s browser here; every other model is a file you download.

0xSero/GLM-5.1-478B-NVFP4 files

0xSero/GLM-5.1-478B-NVFP4 file list, hosted download status, recorded SHA-256 values, manifest links, and source provenance for 5 hosted files out of 5 indexed files.

Task
text generation
Recommended file; this is what downloads
4.1 MB — model-inputscales.safetensors
Size
Recorded total: 305.7 GB · selected file: 4.1 MB
Parameters
478B
Files
5 hosted of 5 listed
Added to Hugging Bay
Updated at source

Download this program

Checked. Ready to download.

GLM-5.1-478B-NVFP4. 1 file. Published by 0xSero

model-inputscales.safetensors · 4.1 MB

Download the file

Run on a computer

On this page you get the files to download, a plain explanation of the model, and the checks that prove the files arrived unchanged.

To run a downloaded model you need the file and a runner app to open it.

Make sure it arrived whole. Usually under a minute

Think of the fingerprint below as the file's ID photo: a string unique to its exact bytes.

What this step does: it only prints an ID string so you can compare; it doesn't run anything or install anything.

On a Mac, the Terminal line below prints this file's SHA-256 fingerprint; it already contains your file's name and assumes the file is in your Downloads folder.

After the download finishes, paste it into Terminal and press Return.

Terminal shasum -a 256 ~/Downloads/model-inputscales.safetensors

On a different computer?

On Windows, the PowerShell line below prints this file's SHA-256 fingerprint; it already contains your file's name and assumes the file is in your Downloads folder.

After the download finishes, paste it into PowerShell and press Enter.

PowerShell Get-FileHash -Algorithm SHA256 "$HOME\Downloads\model-inputscales.safetensors"

From Command Prompt instead: certutil -hashfile "%USERPROFILE%\Downloads\model-inputscales.safetensors" SHA256

PowerShell prints the same SHA-256 fingerprint in capital letters.

On Linux, the terminal line below prints this file's SHA-256 fingerprint; it already contains your file's name and assumes the file is in your Downloads folder.

After the download finishes, paste it into a terminal and press Enter.

Terminal sha256sum ~/Downloads/model-inputscales.safetensors

If the string it prints matches this one, you're holding exactly what we published:

6ac3...e678

File fingerprint (for experts)

6ac3533571950a3a05b33c075244b2487899c6d1a929c71bab0b78a66f7be678

This check proves the file arrived unchanged. Not that the model is safe.

What we've checked:

  • License. Passed (mit)
  • Files hosted. 5 of 5 from the repository
Other files (for experts)

CHAT

A chat model — but here it’s a set of files: download them and load them with a Python library such as Hugging Face transformers on a computer.

You don’t need to know what a “model” is. This is the one for chatting.

Not sure what you’d use it for? Try one question — that’s the whole test. Try: “Explain photosynthesis like I’m five.”

About this download

Not a fact-checker. Not a search engine. It can be confidently wrong.

FAQ

What is this model?

0xSero/GLM-5.1-478B-NVFP4 is an open-weights language model for text generation published by 0xSero, added to Hugging Bay Jun 30, 2026. Model from Hugging Face for text generation: 0xSero/GLM-5.1-478B-NVFP4 · sglang

Can I use it commercially?

It is released under the mit license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

How big is it?

0xSero/GLM-5.1-478B-NVFP4 has 478B parameters. The full upstream repository is 305.7 GB; the recommended download, model-inputscales.safetensors, is 4.1 MB.

What can I download here?

Hugging Bay hosts 5 of 5 files for this model, each with a published SHA-256 checksum. Total size: 305.7 GB. The original release is at https://huggingface.co/0xSero/GLM-5.1-478B-NVFP4.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing — not a safety guarantee. 5 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-0xsero-glm-5-1-478b-nvfp4/safety on Hugging Bay.

Will 0xSero/GLM-5.1-478B-NVFP4 run on my computer?

We can’t check the fit — we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it — you can still download; fit isn’t checked.

Files and download status

5 of 5 indexed files are hosted here, with SHA-256 hashes, manifests, and resumable downloads. Check the Run tab for complete-kit status.

  • chat_template.jinja - 4.6 KB - mirrored-upstream - risk low
  • config.json - 8.1 KB - mirrored-upstream - risk low
  • generation_config.json - 193 B - mirrored-upstream - risk low
  • model-inputscales.safetensors - 3.9 MB - mirrored-upstream - risk low
  • tokenizer_config.json - 723 B - mirrored-upstream - risk low

Files API Hosted downloads API Open interactive files tab

Evidence details

Demand
204 upstream downloads
Trust
Unknown
Download completeness
Hosted file — the exact bytes are complete.
Run fit
Exact selected bytes complete; runtime not established
Scan status
passed
Executable state
complete-bytes
Evidence timestamp
2026-09-19T08:47:07.260Z
Declared license
mit
Pipeline
text-generation
Library
sglang
Task categories
text-generation
Paper ids
2510.13999
File hints
16 upstream file samples