# Groot-19B-A3B-261023

> Groot is a family of open-weight reasoning models for complex real-world tasks. The models are compact and easy to deploy, strong on reasoning and tool-using workloads, and efficient with token budgets.

- **Organisation:** GrootTeam
- **Category:** Vision-Language Models, Reasoning Models
- **Parameters:** 19.4B total, 3B active (MoE)
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-10-23
- **Hugging Face:** 3.4K downloads (30 days), 102 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 7.37 |
| Q3_K_M | 10.41 |
| Q4_K_M | 12.65 |
| Q5_K_M | 14.64 |
| Q6_K | 16.78 |
| Q8_0 | 21.32 |
| F16 | 39.13 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [SGLang](https://selfhost.directory/project/sglang)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LM Studio](https://lmstudio.ai) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

Groot is a family of open-weight reasoning models for complex real-world tasks. The models are compact and easy to deploy, strong on reasoning and tool-using workloads, and efficient with token budgets.

Groot-19B-A3B-261023 has 19B total parameters and activates about 3B per token. It starts from Qwen3.6-35B-A3B and was post-trained on fewer than 0.1B tokens of open-source data. It is the smallest model in its comparison group, yet it scores higher than the larger Qwen3.6-35B-A3B and Gemma-4-26B-A4B, and it gives shorter answers than both.

Where it runs. We release BF16, FP8, NVFP4 and GGUF (Q4_K_M) weights. The device fits below are estimated from memory capacity. BF16 runs on a single 48GB or 80GB GPU (RTX 6000 Ada, A100, H100). FP8 and NVFP4 run the full 256K context on one RTX 5090. GGUF runs on everyday consumer cards: 128K on a 16GB RTX 4060 Ti, 256K on a 24GB RTX 4090 or 3090. It also runs 256K on 128GB unified-memory machines: NVIDIA DGX Spark and other GB10 systems, RTX Spark laptops, AMD Strix Halo mini PCs and Mac M5 Max. Compared with Qwen3.6-35B-A3B: on a 16GB card Groot runs 128K while Qwen3.6 does not load, and on an RTX 5090 Groot runs 256K while Qwen3.6 runs 64K.

## Alternatives

- [Qwen/Qwen3.8-27B](https://selfhost.directory/models/qwen/qwen3.8-27b) (27.8B, Apache 2.0, ≈18.97 GB at Q4): Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
- [google/gemma-4-26B-A4B-it](https://selfhost.directory/models/google/gemma-4-26b-a4b-it) (25.8B (4B active), Apache 2.0, ≈17.67 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [Qwen/Qwen3.6-27B](https://selfhost.directory/models/qwen/qwen3.6-27b) (27.8B, Apache 2.0, ≈18.97 GB at Q4): Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…
- [google/diffusiongemma-26B-A4B-it](https://selfhost.directory/models/google/diffusiongemma-26b-a4b-it) (25.8B (4B active), Apache 2.0, ≈17.68 GB at Q4): DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
- [google/gemma-4-31B-it](https://selfhost.directory/models/google/gemma-4-31b-it) (31.3B, Apache 2.0, ≈26.54 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [Qwen/Qwen3.5-27B](https://selfhost.directory/models/qwen/qwen3.5-27b) (27.8B, Apache 2.0, ≈18.97 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

More: https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/alternatives

## Runs well on

- [Tesla T4](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/tesla-t4): Q4_K_M, est. 97 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/arc-a770): Q4_K_M, est. 169 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/rx-7800-xt): Q4_K_M, est. 189 tok/s
- [Tesla P40](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/tesla-p40): Q8_0, est. 60 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/rx-7900-xtx): Q8_0, est. 166 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/instinct-mi50): Q8_0, est. 177 tok/s

## Similar size

- [moonshotai/Kimi-VL-A3B-Thinking-2506](https://selfhost.directory/models/moonshotai/kimi-vl-a3b-thinking-2506) (16.4B)
- [ServiceNow-AI/Apriel-1.5-15b-Thinker](https://selfhost.directory/models/servicenow-ai/apriel-1.5-15b-thinker) (14.9B)
- [moonshotai/Kimi-VL-A3B-Instruct](https://selfhost.directory/models/moonshotai/kimi-vl-a3b-instruct) (16.4B)
- [microsoft/Phi-4-reasoning-vision-15B](https://selfhost.directory/models/microsoft/phi-4-reasoning-vision-15b) (15.1B)
- [ServiceNow-AI/Apriel-1.6-15b-Thinker](https://selfhost.directory/models/servicenow-ai/apriel-1.6-15b-thinker) (14.9B)
- [OpenGVLab/InternVL3_5-14B](https://selfhost.directory/models/opengvlab/internvl3_5-14b) (15.1B)

## FAQ

**How much VRAM does Groot-19B-A3B-261023 need?**
About 13 GB at Q4_K_M with an 8K context. Q8_0 needs about 21 GB and full precision about 39 GB. Longer contexts need more memory for the KV cache.

**Can Groot-19B-A3B-261023 run on the Tesla T4?**
Yes. It fits at Q4_K_M (about 13 GB), at an estimated 97 tokens/s. It fits comfortably on the Arc A770 16GB, Radeon RX 7800 XT, Tesla P40.

**Can I use Groot-19B-A3B-261023 commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of Groot-19B-A3B-261023?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

**How do I run Groot-19B-A3B-261023 with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q4_K_M. With llama.cpp: llama-server -hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/GrootTeam/Groot-19B-A3B-261023

---
Source: https://selfhost.directory/models/grootteam/groot-19b-a3b-261023