dolphin3.0-llama3.2-3B-4Bit
mlx-community/dolphin3.0-llama3.2-3B-4BitContent controls: not assessed.
Model from Hugging Face for llm: mlx-community/dolphin3.0-llama3.2-3B-4Bit · mlx
Informações do modelo
dolphin3.0-llama3.2-3B-4Bit is an open-weights language model for general. The primary file is model.safetensors (1.81 GB). The primary file needs about 3 GB free for the selected file. License: Llama 3.2 Community. The SHA-256 prefix is 233e9cffdff7. 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.
O que está incluído
5 hosted of 8 listed
Sobre este modelo
External Hugging Face catalog record for mlx-community/dolphin3.0-llama3.2-3B-4Bit. Library: mlx. Languages: en. Datasets referenced by card metadata: OpenCoder-LLM/opc-sft-stage1, OpenCoder-LLM/opc-sft-stage2, microsoft/orca-agentinstruct-1M-v1, microsoft/orca-math-word-problems-200k, NousResearch/hermes-function-calling-v1, AI-MO/NuminaMath-CoT. Base model: cognitivecomputations/Dolphin3.0-Llama3.2-3B. Popularity signal at import: 3,049 downloads and 3 likes.
Informações básicas
- Parameters
- 3B
- Hosted here
- 5 hosted of 8 listed
- Full repo upstream
- 1.82 GB
- Recommended file
- 1.81 GB · model.safetensors
- Languages
- en
- Format
- safetensors
- Downloads on Hugging Face
- 3,049
- File hashes
- Hashes recorded. Date not recorded.
Licença e origem
License: llama3.2
Check the license text and keep the required notices when you use or share the files.
Upstream source →- License
- Llama 3.2 Community. Custom terms, read before use
- Task
- general
- Hosted here
- at least 5 listed files; full count and size unknown
- Full repo upstream
- 1.82 GB
- Recommended file
- 1.81 GB · model.safetensors
- Parameters
- 3B
- Files
- 5 hosted of 8 listed
- Download
- Download here (5 hosted files)
- Added to Hugging Bay
- Updated at source
FAQ
What is this model?
mlx-community/dolphin3.0-llama3.2-3B-4Bit is an open-weights language model for general published by mlx-community, added to Hugging Bay Sep 18, 2026. Model from Hugging Face for llm: mlx-community/dolphin3.0-llama3.2-3B-4Bit · mlx
Can I use it commercially?
It is released under the llama3.2 license. Commercial use is allowed with conditions. Commercial use is permitted with obligations: Llama community license: commercial use allowed; if your products/services exceeded 700 million monthly active users (Section 2, Additional Commercial Terms) you must request a license from Meta first; the acceptable-use policy and attribution notice apply.
How big is it?
mlx-community/dolphin3.0-llama3.2-3B-4Bit has 3B parameters. Hosted here: at least 5 listed files; full count and size unknown. Full repo upstream: 1.82 GB. The recommended download, model.safetensors, is 1.81 GB.
What can I download here?
Hosted here: at least 5 listed files; full count and size unknown. Full repo upstream: 1.82 GB. The original release is at https://huggingface.co/mlx-community/dolphin3.0-llama3.2-3B-4Bit.
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-mlx-community-dolphin3-0-llama3-2-3b-4bit/safety on Hugging Bay.
Will mlx-community/dolphin3.0-llama3.2-3B-4Bit 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 cognitivecomputations/dolphin3.0-llama3.2-3b (from the publisher card on Hugging Face). This does not mean the files match the original weights.
1 other repack declare the same base on their cards.