Dolphin 3.0 8B
Dolphin 3.0 8B is Cognitive Computations' general-purpose fine-tune on a Llama 3.1 8B base, with content filtering removed by design. It is the most-pulled uncensored general-purpose model on Ollama, part of a Dolphin series that accounts for 5 of the top 10 spots in Ollama's uncensored catalog by download count.
Overview
Dolphin 3.0 8B is Cognitive Computations' general-purpose fine-tune on a Llama 3.1 8B base, with content filtering removed by design. It is the most-pulled uncensored general-purpose model on Ollama, part of a Dolphin series that accounts for 5 of the top 10 spots in Ollama's uncensored catalog by download count.
Strengths
- Highest pull count among current-generation uncensored general models
- Llama 3.1 Community License permits commercial use
- Supports function calling with a configurable 8K-256K context window
Weaknesses
- No content filtering by design — unsuitable for consumer-facing deployments without a moderation layer
- Fine-tune quality inherits the limitations of its Llama 3.1 8B base
- Community fine-tune, not vendor-benchmarked against standard suites
Reviewed quality benchmarks
First-party rows were run by RunLocalAI; reviewed community rows are labeled in the data. Every row links to the raw test-run log.
| Benchmark | Quant | Runtime / Hardware | Score | Raw log |
|---|---|---|---|---|
HumanEval+ tested 2026-07-20 | Q4_K_M | ollama-0.32.1-vast5090 rtx-5090 | 56.7/100 | Gist → |
Q4_K_M note:First-party HumanEval+ on a rented Vast.ai RTX 5090 32GB instance via Ollama 0.32.1. Generation via evalplus_openai_generate.py, scoring via evalplus.evaluate (native Linux, no Windows shim needed). No DB credentials were placed on the rented host — results were pulled back and ingested from the operator's machine.
Want to verify? Every row links to its Gist with full stdout and stderr of the run. The runner script is in the public repo (scripts/run-humaneval-plus.ts) — reproducible end-to-end. Browse all coding scores at /benchmarks/coding.
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 | 5.0 GB | 7 GB |
Get the model
Ollama
One-line install
ollama run dolphin3:8bRead our Ollama review →Hardware that runs this
Cards with enough VRAM for at least one quantization of Dolphin 3.0 8B.
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 8B?
Can I use Dolphin 3.0 8B commercially?
What's the context length of Dolphin 3.0 8B?
How do I install Dolphin 3.0 8B with Ollama?
Source: Vendor official documentation
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Dolphin 3.0 8B runs on your specific hardware before committing money.