MiniCPM5-2B-MLX-8bit safetensors download | Hugging Bay

Q: What is this model?

abenzerps/MiniCPM5-2B-MLX-8bit is an open-weights language model for text generation published by abenzerps, added to Hugging Bay Sep 22, 2026. Model from Hugging Face for text generation: abenzerps/MiniCPM5-2B-MLX-8bit · mlx

Q: 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.

Q: How big is it?

abenzerps/MiniCPM5-2B-MLX-8bit has 2B parameters. Hosted here: at least 6 listed files; full count and size unknown. Full repo upstream: 2.68 GB. The recommended download, model.safetensors, is 2.67 GB.

Q: What can I download here?

Hosted here: at least 6 listed files; full count and size unknown. Full repo upstream: 2.68 GB. The original release is at https://huggingface.co/abenzerps/MiniCPM5-2B-MLX-8bit.

Q: File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 6 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-abenzerps-minicpm5-2b-mlx-8bit/safety on Hugging Bay.

Q: Will abenzerps/MiniCPM5-2B-MLX-8bit 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.

abenzerps

MiniCPM5-2B-MLX-8bit

abenzerps/MiniCPM5-2B-MLX-8bit

text generationLicense: apache-2.0Hashes recordedsafetensors

Content controls: not assessed.

Model from Hugging Face for text generation: abenzerps/MiniCPM5-2B-MLX-8bit · mlx

View as JSON →

6 hosted of 12 listed

Hashes recorded. Date not recorded.

File	आकार	SHA-256	स्रोत	डाउनलोड करें
Weights
`model.safetensors` Default	2.67 GB	`ecdd3744…c79b4533` `ecdd3744665367b62a93c201ab911b1176373b0fede9210ae9e7cc63c79b4533`	Hosted	डाउनलोड करें
Tokenizer & config
`SHA256SUMS.txt`	124 bytes	—	Upstream only	File metadata
`assets/minicpm5-benchmark.png`	34.9 KB	—	Upstream only	File metadata
`assets/minicpm5-benchmark2.png`	66.4 KB	—	Upstream only	File metadata
`config.json`	886 bytes	`aa0fa827…3f8a104f` `aa0fa827a83a29f2bc8b1b9c681914b0689554762f11f3d7240725133f8a104f`	Hosted	डाउनलोड करें
`model.safetensors.index.json`	68.7 KB	—	Upstream only	File metadata
`tokenizer_config.json`	435 bytes	`b89503c3…a61448a9` `b89503c3e5070c6b6d33daf2e20cb4a5c88537c1670d9b7e0cfb4506a61448a9`	Hosted	डाउनलोड करें
`chat_template.jinja`	9.06 KB	`cc945752…2e9fcf1c` `cc945752db555d60949b16989df4ccfeb52a313d6b4b5c5229dd786e2e9fcf1c`	Hosted	डाउनलोड करें
`generation_config.json`	213 bytes	`9ac4f32e…c122fdb1` `9ac4f32e5f32358697a9f438a3ea89ef80e6ba786c72c49e932f9f21c122fdb1`	Hosted	डाउनलोड करें
`tokenizer.json`	9.89 MB	`3e065a55…171fed81` `3e065a558a034185fe299917b398685c1facd0169a9eea1e629eb30c171fed81`	Hosted	डाउनलोड करें
Docs
`.gitattributes`	54 bytes	—	Upstream only	File metadata
`README.md`	1.51 KB	—	Upstream only	File metadata

डाउनलोड की जाँच करें

In the folder where you saved model.safetensors, run:

macOS

shasum -a 256 -- 'model.safetensors'

Linux

sha256sum -- 'model.safetensors'

Windows

Get-FileHash -LiteralPath 'model.safetensors' -Algorithm SHA256

Compare the result with the recorded SHA-256.

MiniCPM5-2B-MLX-8bit

डाउनलोड की जाँच करें

Cookies