跳转到主要内容

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.

cstr

MOSS-Transcribe-preview-2B-GGUF

cstr/MOSS-Transcribe-preview-2B-GGUF
speech recognitionLicense: apache-2.0Hashes recordedGGUF

Content controls: not assessed.

Model from Hugging Face for automatic speech recognition: cstr/MOSS-Transcribe-preview-2B-GGUF · ggml

模型信息

MOSS-Transcribe-preview-2B-GGUF is an audio model for speech recognition. The primary file is moss-transcribe-preview-2b-q8_0.gguf (3.52 GB, Q8_0). The primary file needs about 5 GB free for the Q8 file. License: Apache 2.0. The SHA-256 prefix is 4211f7f0b847. The primary Download is available now. No tested run commands for this file yet. See Files for current download availability. The size and hash details refer to the selected file, not every file in the repository. The memory figure is estimated from recorded file size with working room included. The size line uses recorded file bytes when they are present in this model record.

包含内容

1 hosted of 8 listed

Weights
README, LICENSE & .gitattributes

关于此模型

External Hugging Face catalog record for cstr/MOSS-Transcribe-preview-2B-GGUF. Task: automatic speech recognition. Library: ggml. Languages: en, zh. Base model: OpenMOSS-Team/MOSS-Transcribe-preview-2B. Popularity signal at import: 880 downloads and 0 likes.

基本信息

Parameters
2B
Hosted here
1 hosted of 8 listed
Full repo upstream
16.6 GB
Recommended file
3.52 GB (Q8_0) · moss-transcribe-preview-2b-q8_0.gguf
Languages
en, zh
Format
GGUF
Downloads on Hugging Face
880
File hashes
Hashes recorded. Date not recorded.

许可证与来源

License: apache-2.0

Check the license text and keep the required notices when you use or share the files.

Upstream source →

See the JSON record →

Task
speech recognition
Hosted here
1 file, 3.52 GB
Full repo upstream
16.6 GB
Recommended file
3.52 GB (Q8_0) · moss-transcribe-preview-2b-q8_0.gguf
Parameters
2B
Files
1 hosted of 8 listed
Added to Hugging Bay
Updated at source

FAQ

What is this model?

cstr/MOSS-Transcribe-preview-2B-GGUF is an audio model for speech recognition published by cstr, added to Hugging Bay Sep 22, 2026. Model from Hugging Face for automatic speech recognition: cstr/MOSS-Transcribe-preview-2B-GGUF · ggml

Can I use it commercially?

It is released under the apache-2.0 license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

How big is it?

cstr/MOSS-Transcribe-preview-2B-GGUF has 2B parameters. Hosted here: 1 file, 3.52 GB. Full repo upstream: 16.6 GB. The recommended download, moss-transcribe-preview-2b-q8_0.gguf (Q8_0), is 3.52 GB.

What can I download here?

Hosted here: 1 file, 3.52 GB. Full repo upstream: 16.6 GB. The original release is at https://huggingface.co/cstr/MOSS-Transcribe-preview-2B-GGUF.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 1 hosted file carries a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-cstr-moss-transcribe-preview-2b-gguf/safety on Hugging Bay.

Will cstr/MOSS-Transcribe-preview-2B-GGUF 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.

Repack of openmoss-team/moss-transcribe-preview-2b (from the publisher card on Hugging Face). This does not mean the files match the original weights.