Dolphin 3.0 Llama 3.2 3B
Eric Hartford's Dolphin fine-tune at 3B. Less-censored than the base Llama; popular for unconstrained-generation use cases.
Overview
Eric Hartford's Dolphin fine-tune at 3B. Less-censored than the base Llama; popular for unconstrained-generation use cases.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- Less censored than base
- Strong creative-writing benchmarks
Weaknesses
- Smaller community than Llama base
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 1.8 GB | 3 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Dolphin 3.0 Llama 3.2 3B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Dolphin 3.0 Llama 3.2 3B?
Can I use Dolphin 3.0 Llama 3.2 3B commercially?
What's the context length of Dolphin 3.0 Llama 3.2 3B?
Source: huggingface.co/cognitivecomputations/Dolphin3.0-Llama3.2-3B
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Dolphin 3.0 Llama 3.2 3B runs on your specific hardware before committing money.