---
title: vllm-sr/d3-turbo
url: https://recentmodel.com/models/vllm-sr/d3-turbo/
status: main board
published: 2026-10-19T02:14:31Z
updated: 2026-10-19T23:17:53Z
source: https://huggingface.co/vllm-sr/d3-turbo
---

# vllm-sr/d3-turbo

d3-turbo is the upgraded 27B multimodal decision model of Decision 3.0, the decision models of vLLM Semantic Router. Dense, 26B params. Context: 256K tokens (config). License: apache-2.0.


- **Org:** vllm-sr
- **Released:** 2026-10-19
- **Status:** main board
- **License:** apache-2.0 (permissive)
- **Parameters:** 26.1B
- **Architecture:** dense · Qwen3_5Model
- **Context:** 262,144 tokens
- **Task:** zero-shot-classification · other
- **Signal:** 92 HF likes · 1549 downloads

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~18.8 GB (estimated): 24GB GPU (3090 / 4090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~30.8 GB (estimated): 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), Arc B70 32GB, Mac 48GB, Mac 64GB (M1 Max)
- FP16 ~55.3 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/vllm-sr/d3-turbo)
- [Ollama](https://ollama.com/library/d3)