Rio-3.0-Open-Mini
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve prefeitura-rio/Rio-3.0-Open-MiniNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Rio-3.0-Open-Mini
Rio-3.0-Open-Mini is a 4B-parameter mit model from prefeitura-rio. At Q4_K_M it needs roughly 2 GB of VRAM, placing it in the cpu hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 4B |
| Context length | 262K tokens |
| License | mit |
| Modalities | text |
| Released | 2026-02-09 |
| Weights | prefeitura-rio/Rio-3.0-Open-Mini |
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~2 GB | RTX 4060, RTX 3060 8GB |
| Q5_K_M | ~3 GB | RTX 4060, RTX 3060 8GB |
| Q8_0 | ~4 GB | RTX 4060, RTX 3060 8GB |
| FP16 | ~8 GB | RTX 4060, RTX 3060 8GB |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve prefeitura-rio/Rio-3.0-Open-MiniPopularity
Rio-3.0-Open-Mini has 2,327,782 downloads in the last month on HuggingFace and 8 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Rio-3.0-Open-Mini need?
Rio-3.0-Open-Mini with 4B parameters needs approximately 2 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Rio-3.0-Open-Mini better than other prefeitura-rio models?
Rio-3.0-Open-Mini has 4B parameters with 262,144 context - a strong choice for general use.
What license is Rio-3.0-Open-Mini under?
Rio-3.0-Open-Mini is released under the mit license, making it suitable for most commercial and personal projects.
What hardware runs Rio-3.0-Open-Mini well?
With 4B parameters, Rio-3.0-Open-Mini requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Rio-3.0-Open-Mini?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~3 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Rio-3.0-Open-Mini's context window handle?
Rio-3.0-Open-Mini supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Rio-3.0-Open-Mini?
Rio-3.0-Open-Mini competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec
Comments coming soon
Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.