# mlx-community/dolphin3.0-llama3.2-3B-4Bit

Model from Hugging Face for llm: mlx-community/dolphin3.0-llama3.2-3B-4Bit · mlx

## Facts

- Type: LLM
- Task: general
- Framework: mlx
- License: llama3.2 — 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.
- Source: https://huggingface.co/mlx-community/dolphin3.0-llama3.2-3B-4Bit
- Hosting: hosted (5 files)
- Files: 5 hosted of 8 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 5 files, 1.82 GB
- Full repo upstream: 1.82 GB
- Recommended file: 1.81 GB · model.safetensors
- Parameters: 3B
- Download: https://huggingbay.xyz/artifact/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/download-plan)
- Per-file SHA-256: available for 5 of 5 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 3049
- Stars: 3
- Card completeness: 95%

## Description

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.

## Model Card Facts

- Declared license: llama3.2
- Pipeline: general
- Library: mlx
- Base model: cognitivecomputations/Dolphin3.0-Llama3.2-3B
- Task categories: general
- Languages: en
- Referenced datasets: 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, AI-MO/NuminaMath-TIR, allenai/tulu-3-sft-mixture
- File hints: 8 upstream file samples

## Referenced Data

- Dataset: OpenCoder-LLM/opc-sft-stage1
- Dataset: OpenCoder-LLM/opc-sft-stage2
- Dataset: microsoft/orca-agentinstruct-1M-v1
- Dataset: microsoft/orca-math-word-problems-200k
- Dataset: NousResearch/hermes-function-calling-v1
- Dataset: AI-MO/NuminaMath-CoT
- Dataset: AI-MO/NuminaMath-TIR
- Dataset: allenai/tulu-3-sft-mixture
- Dataset: cognitivecomputations/dolphin-coder
- Dataset: HuggingFaceTB/smoltalk
- Dataset: cognitivecomputations/samantha-data
- Dataset: m-a-p/CodeFeedback-Filtered-Instruction

## File Hints

- .gitattributes (1.5 KB)
- README.md (1.3 KB)
- config.json (1.1 KB)
- model.safetensors (1.7 GB) LFS
- model.safetensors.index.json (45 KB)
- special_tokens_map.json (444 B)
- tokenizer.json (16 MB) LFS
- tokenizer_config.json (50 KB)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: review
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-18T22:42:53.626Z.
- Upstream license: llama3.2. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model card references dataset context: OpenCoder-LLM/opc-sft-stage1, OpenCoder-LLM/opc-sft-stage2, microsoft/orca-agentinstruct-1M-v1, microsoft/orca-math-word-problems-200k.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-mlx-community-dolphin3-0-llama3-2-3b-4bit/decentralized-fallbacks