deepseek-coder-33B-instruct-GGUF GGUF download | Hugging Bay

deepseek-coder-33B-instruct-GGUF

Can I run deepseek-coder-33B-instruct-GGUF on my computer?

It depends on your memory, processor, file format and runtime. Hugging Bay offers 1 hosted file; check the file list for the exact selection. A file-size fit is an estimate, not a successful run or speed promise. Read the license before use.

deepseek-coder-33B-instruct-GGUF is an open-weights language model for general. Model weights are learned parameters; a runtime loads them. A hosted file is an individual file Hugging Bay can serve. SHA-256 identifies exact file bytes. The availability date above applies to this file record, not the upstream metadata update date.

As of the recorded file availability check on 2026-10-22.

Recorded SHA-256 for deepseek-coder-33b-instruct.Q4_K_M.gguf: e76518575f9d367b0a04278cd027c51e53519506b4316b4d368e853a42bfe790. Exact file evidence · Machine-readable source facts · Run evidence and any recorded receipts. A checksum fingerprints only the named file bytes; it does not prove safety, quality, a complete multi-file selection or a successful run.

Updated 2026-10-21 · Page-copy source revision 8871bab84e1cf80aea1686a944ec335078a6c036 · Source files: apps/web/lib/model-page-template.mjs, apps/web/lib/model-page-v3.mjs, apps/web/lib/aeo-page.mjs · Full revision record

Model metadata: As of 2026-09-20 at the model source. Popularity counters are source-reported, not measured by Hugging Bay. Availability checked 2026-10-22.

TheBloke/deepseek-coder-33B-instruct-GGUF

Model details

generalLicense: deepseek (custom terms)SHA-256 recorded for 12 of 15 filesGGUF

Content controls: not assessed.

The catalog does not give enough information to describe what this model is for. Catalog sources: baseModel.

View as JSON →

Your next step

Use it from code

This Python snippet downloads the selected file. Running the model needs its own library and setup.

from urllib.request import urlretrieve

urlretrieve(
    "https://huggingbay.xyz/api/downloads/hf-model-thebloke-deepseek-coder-33b-instruct-gguf/deepseek-coder-33b-instruct.Q4_K_M.gguf",
    "deepseek-coder-33b-instruct.Q4_K_M.gguf",
)

Other ways

Run it on your computerOpen in Hugging Bay appSend to a computerMac (Apple silicon) and Linux x86_64 installs are listed on the download page. Windows and Intel Mac are not yet. The app checks this model before you choose to download.

1 hosted of 15 listed · Hashes recorded. Date not recorded.

Selected downloaddeepseek-coder-33b-instruct.Q4_K_M.gguf19.94 GB · 1 file Download · 19.94 GB (1 file)

Open-file help

Content controls: not assessed.

Check your download →

Compare your file’s SHA-256 with the recorded hash.

Informações do modelo

deepseek-coder-33B-instruct-GGUF is an open-weights language model for general. The primary file is deepseek-coder-33b-instruct.Q4_K_M.gguf (19.94 GB, Q4_K_M). The primary file needs about 24 GB free for the Q4 file (file plus room to run it). License: unknown. The SHA-256 prefix is e76518575f9d. The primary Download is available now. No tested run commands for this file yet. The license label is unknown; availability is shown separately. 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.

O que está incluído

1 hosted of 15 listed

Weights

Tokenizer & config

README, LICENSE & .gitattributes

Sobre este modelo

External Hugging Face catalog record for TheBloke/deepseek-coder-33B-instruct-GGUF. Library: transformers. Base model: deepseek-ai/deepseek-coder-33b-instruct. Popularity signal at import: 19,377 downloads and 194 likes.

Informações básicas

Parameters: 33B
Hosted here: 1 hosted of 15 listed
Full repo upstream: 252 GB
Recommended file: 19.9 GB (Q4_K_M) · deepseek-coder-33b-instruct.Q4_K_M.gguf
Format: GGUF
File hashes: Hashes recorded. Date not recorded.

Licença e origem

License: deepseek (custom terms)

1 hosted of 15 listed

The model's publisher names its own license (deepseek). We have not checked its terms. Read them before you use or share the files.

See the JSON record →

Download check: Can download · bytes verified · signed · current
Checked: 2026-10-22T05:33:04.292Z
License: deepseek (custom terms)
Task: general
Hosted here: 1 file, 19.9 GB
Full repo upstream: 252 GB
Recommended file: 19.9 GB (Q4_K_M) · deepseek-coder-33b-instruct.Q4_K_M.gguf
Parameters: 33B
Files: 1 hosted of 15 listed
Download: Download here (1 hosted file)
Added to Hugging Bay: Sep 20, 2026
Updated at source: Sep 20, 2026
Source: TheBloke/deepseek-coder-33B-instruct-GGUF

FAQ

What is this model?

TheBloke/deepseek-coder-33B-instruct-GGUF is an open-weights language model for general published by TheBloke, added to Hugging Bay Sep 20, 2026. Model from Hugging Face for llm: TheBloke/deepseek-coder-33B-instruct-GGUF · transformers

Can I use it commercially?

License: deepseek (custom terms). We have not checked these terms. Read them or ask the model author before commercial use.

How big is it?

TheBloke/deepseek-coder-33B-instruct-GGUF has 33B parameters. Hosted here: 1 file, 19.9 GB. Full repo upstream: 252 GB. The recommended download, deepseek-coder-33b-instruct.Q4_K_M.gguf (Q4_K_M), is 19.9 GB.

What can I download here?

Hosted here: 1 file, 19.9 GB. Full repo upstream: 252 GB.

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-thebloke-deepseek-coder-33b-instruct-gguf/safety on Hugging Bay.

Will TheBloke/deepseek-coder-33B-instruct-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 deepseek-ai/deepseek-coder-33b-instruct (from the publisher card on Hugging Face). This does not mean the files match the original weights.