GR

Groot 19B A3B 261023

GrootGGUF by mradermacherUpdated 2026-10-25
Download on Hugging Face
Parameters19B
Context256K
Layers41
Architectureqwen35moe
Smallest quant0.2 GB
Quick answer

Groot 19B A3B 261023 needs about 12.8 GB of memory at Q4_K_M (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 16 quants, from 0.2 GB to 15.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Groot 19B A3B 261023 – compact reasoning model with 19B parameters

Groot 19B A3B 261023 is a 19B parameter model that activates about 3B per token. It is a mixture of experts based on qwen35moe architecture and is trained on fewer than 0.1B open‑source tokens. The model supports reasoning and tool‑using workloads and runs with a 262144 token context.

Good at

  • Reasoning
  • Tool usage
  • Efficient token budgets

Limits

  • No vision support
  • Requires at least 8GB VRAM for Q4_K_M
  • License is apache‑2.0

Best for

  • Complex reasoning tasks
  • Tool‑integrated workflows
  • Deploy on consumer GPUs

Who it’s for. Developers needing a small yet capable reasoning model for local deployment. The model is open‑weight and can be run on consumer GPUs with GGUF quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.4 GB
Fits Get file →
Q2_K7.2 GB 8.4 GB
Too big Get file →
Q3_K_S8.4 GB 9.6 GB
Too big Get file →
IQ3_S8.5 GB 9.7 GB
Too big Get file →
IQ3_M8.6 GB 9.8 GB
Too big Get file →
Q3_K_M9.3 GB 10.5 GB
Too big Get file →
Q3_K_L10.0 GB 11.2 GB
Too big Get file →
IQ4_XS10.4 GB 11.6 GB
Too big Get file →
Q4_010.9 GB 12.1 GB
Too big Get file →
IQ4_NL10.9 GB 12.1 GB
Too big Get file →
Q4_K_S11.0 GB 12.1 GB
Too big Get file →
Q4_K_M11.7 GB 12.8 GB
Too big Get file →
Q4_112.0 GB 13.2 GB
Too big Get file →
Q5_K_S13.2 GB 14.4 GB
Too big Get file →
Q5_K_M13.6 GB 14.8 GB
Too big Get file →
Q6_K15.6 GB 16.8 GB
Too big Get file →

For 8GB VRAM use Q4_K_M (file size 11.66GB, estimated 12.8GB memory at 8k context). For 16GB VRAM use Q3_K_L (file size 10GB, estimated 11.2GB memory). For 24GB VRAM use Q5_K_M (file size 13.58GB, estimated 14.8GB memory).

What GPU do you need for Groot 19B A3B 261023?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ4_XS (10.4 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (13.6 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (15.6 GB file, about 16.8 GB in use).

Which Groot 19B A3B 261023 quant should you choose?

Q4_K_M is the usual starting point for Groot 19B A3B 261023: it balances file size and quality well. Here it is a 11.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters19B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bymradermacher
FamilyGroot
Licenseapache-2.0
Downloads (HF)3,193
Last updated2026-10-25

Frequently asked questions about Groot 19B A3B 261023

How much VRAM does Groot 19B A3B 261023 need?

About 12.8 GB at Q4_K_M with an 8K context window. That is the 11.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Groot 19B A3B 261023 on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Groot 19B A3B 261023 GGUF?

It depends on the quant: file is 0.2 GB, Q2_K is 7.2 GB, Q3_K_S is 8.4 GB, IQ3_S is 8.5 GB, IQ3_M is 8.6 GB, Q3_K_M is 9.3 GB and 10 more.

What context length does Groot 19B A3B 261023 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download Groot 19B A3B 261023 GGUF?

The files are on Hugging Face in the mradermacher/Groot-19B-A3B-261023-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Groot 19B A3B 261023 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Groot 19B A3B on a 16GB RTX 4060 Ti?

Yes, the Q4_K_M quant runs 128K context on a 16GB RTX 4060 Ti with estimated 12.8GB memory usage.

Does this model support vision tasks?

No, the model is a text‑only model; vision support is not provided.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Groot-19B-A3B-261023

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Groot models

All Groot →

Other medium models

All medium models →