# Can the Instinct MI50 32GB run Groot-19B-A3B-261023?

> Yes. The Instinct MI50 32GB runs Groot-19B-A3B-261023 fully in VRAM at Q8_0 (about 21 GB of 32 GB), at roughly 177 tokens/s.

Instinct MI50 32GB: 32 GB (32 GB usable), 1024 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 8.84 | fits | 571 |
| Q3_K_M | Noticeable loss | 10.54 | fits | 384 |
| Q4_K_M | Small loss | 13.34 | fits | 310 |
| Q5_K_M | Near-lossless | 15.53 | fits | 264 |
| Q6_K | Near-lossless | 17.55 | fits | 228 |
| Q8_0 (pick) | Lossless | 20.91 | fits | 177 |
| F16 | Lossless | 38.3 | offload | 26 |

## Run it

Q8_0 straight from Hugging Face (ollama):

```bash
ollama run hf.co/bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q8_0
```

OpenAI-compatible server with a web UI (llama.cpp):

```bash
llama-server -hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q8_0
```

Docker with Vulkan (llama.cpp):

```bash
docker run -d --name llama --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-vulkan \
  -hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99
```

Download with the lms CLI (lmstudio):

```bash
lms get bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF@Q8_0
```

Ask about an image (transformers):

```python
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"])
```


## Vision models that fit comfortably

- [google/gemma-4-26B-A4B-it](https://selfhost.directory/models/google/gemma-4-26b-a4b-it/on/instinct-mi50): Q8_0 ≈28.65 GB, est. 133 tok/s
- [Qwen/Qwen3.8-27B](https://selfhost.directory/models/qwen/qwen3.8-27b/on/instinct-mi50): Q6_K ≈24.88 GB, est. 25 tok/s
- [Qwen/Qwen3.6-27B](https://selfhost.directory/models/qwen/qwen3.6-27b/on/instinct-mi50): Q6_K ≈24.53 GB, est. 25 tok/s
- [google/gemma-4-31B-it](https://selfhost.directory/models/google/gemma-4-31b-it/on/instinct-mi50): Q5_K_M ≈29.18 GB, est. 25 tok/s
- [google/gemma-3-27b-it](https://selfhost.directory/models/google/gemma-3-27b-it/on/instinct-mi50): Q6_K ≈26.05 GB, est. 25 tok/s
- [Qwen/Qwen3.5-27B](https://selfhost.directory/models/qwen/qwen3.5-27b/on/instinct-mi50): Q6_K ≈24.46 GB, est. 25 tok/s

## Other GPUs that run it

- [Apple M4 (16 GB)](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/apple-m4-16gb): Q3_K_M, est. 45 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/rx-6700-xt): Q3_K_M, est. 144 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/rtx-3060): Q3_K_M, est. 135 tok/s
- [Arc B580](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/arc-b580): Q3_K_M, est. 171 tok/s
- [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

---
Model: https://selfhost.directory/models/grootteam/groot-19b-a3b-261023. GPU: https://selfhost.directory/models/gpus/instinct-mi50. Source: https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/instinct-mi50