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.
Groot-19B-A3B-261023
GrootTeam·Instruct·released 23 Oct 2026
ollama run hf.co/bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q4_K_MGroot 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.
How much VRAM does Groot-19B-A3B-261023 need?
At Q4_K_M Groot-19B-A3B-261023 needs about 13 GB with an 8K context (13 GB at Q4, 39 GB at full precision). Pick your GPU to see what fits and how fast it runs.
Needs: ≈13 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.
Advanced: context 8K · KV cache 16-bit
Smallest GPU for each quant and context (KV cache 16-bit)
| Quantisation | 8K | 16K | 32K | 64K | 128K | 256K |
|---|---|---|---|---|---|---|
| Q3_K_M | ||||||
| Q4_K_M | ||||||
| Q5_K_M | ||||||
| Q6_K | ||||||
| Q8_0 | ||||||
| FP16 |
≤16 GB card24–32 GB48–96 GBmore
| Quantisation | Total |
|---|---|
| Q2_KHeavy lossSmallest, noticeably worse quality | ≈8.8 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈11 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈13 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈16 GB |
| Q6_KNear-losslessPractically lossless | ≈18 GB |
| Q8_0LosslessLossless in practice, twice the size of Q4 | ≈21 GB |
| FP16 / BF16LosslessFull precision, as released | ≈38 GB |
Estimates for 8K tokens of context: weights + KV cache + runtime overhead. All experts stay in memory, but only the active ones are read per token. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
How to pick a quant
Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.
- LosslessF16, Q8_0
- Near-losslessQ6_K, Q5_K_M
- Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
- Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
- Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K
Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B
How much context fits?
At 8K context, Q4_K_M needs ≈13 GB(12 GB weights + 0.6 GB KV cache + 1.1 GB overhead). Pick a GPU above to see how much context fits.
Weights + overheadKV cache
Can the Tesla T4 run Groot-19B-A3B-261023? →
Speed vs quality per quant
Smaller quants run faster and fit in less memory, but lose quality.
Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.
Real-world speed of Groot-19B-A3B-261023
Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →
No medians yet. Be one of the first 3 to report a setup.
All reports
Run Groot-19B-A3B-261023 locally
--quantQ4_K_Mdefault; pick your GPU to tailor itbartowski/GrootTeam_Groot-19B-A3B-261023-GGUF
ollama run hf.co/bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q4_K_M llama-server -hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q4_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
vllm serve GrootTeam/Groot-19B-A3B-261023services:
vllm:
image: vllm/vllm-openai:latest
command: GrootTeam/Groot-19B-A3B-261023
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve GrootTeam/Groot-19B-A3B-261023 --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve GrootTeam/Groot-19B-A3B-261023 --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="GrootTeam/Groot-19B-A3B-261023", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| guitaripod/groot-19b-a3b-uncensored-nvfp4 | Safetensors | NVFP4 | — |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | IQ2_S | 6.7 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | IQ2_M | 7.3 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | Q2_K | 7.9 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | IQ3_XXS | 8.8 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | Q3_K_S | 9.0 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | IQ3_XS | 9.0 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | Q3_K_M | 9.6 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | Q3_K_L | 10 GB |
| bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF | GGUF | IQ3_M | 11 GB |
About 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. 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.
Full model card on Hugging Face →Alternatives to Groot-19B-A3B-261023
All alternatives →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.
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…
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.
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.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
Groot-19B-A3B-261023 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.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments