# Can the Instinct MI50 32GB run HuatuoGPT-3-27B?

> Yes. The Instinct MI50 32GB runs HuatuoGPT-3-27B fully in VRAM at Q6_K (about 24 GB of 32 GB), at roughly 25 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 | 12.98 | fits | 63 |
| Q3_K_M | Noticeable loss | 15.51 | fits | 43 |
| Q4_K_M | Small loss | 18.68 | fits | 34 |
| Q5_K_M | Near-lossless | 21.31 | fits | 29 |
| Q6_K (pick) | Near-lossless | 24.1 | fits | 25 |
| Q8_0 | Lossless | 30.55 | tight | 20 |
| F16 | Lossless | 55.31 | offload | 1.3 |

## Run it

Q6_K straight from Hugging Face (ollama):

```bash
ollama run hf.co/mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q6_K
```

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

```bash
llama-server -hf mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q6_K
```

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 mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99
```

Download with the lms CLI (lmstudio):

```bash
lms get mradermacher/HuatuoGPT-3-27B-i1-GGUF@Q6_K
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="FreedomIntelligence/HuatuoGPT-3-27B", 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

- [Qwen/Qwen3.8-27B](https://selfhost.directory/models/qwen/qwen3.8-27b/on/instinct-mi50): Q6_K ≈24.88 GB, est. 25 tok/s
- [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/Qwen3.6-27B](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

- [Tesla T4](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/tesla-t4): Q3_K_M, est. 13 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/arc-a770): Q3_K_M, est. 23 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/rx-7800-xt): Q3_K_M, est. 26 tok/s
- [Tesla P40](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/tesla-p40): Q5_K_M, est. 9.9 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/rx-7900-xtx): Q5_K_M, est. 27 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/rtx-5090): Q6_K, est. 44 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/apple-m4-pro-48gb): Q8_0, est. 5.2 tok/s
- [RTX A6000](https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/rtx-a6000): Q8_0, est. 15 tok/s

---
Model: https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b. GPU: https://selfhost.directory/models/gpus/instinct-mi50. Source: https://selfhost.directory/models/freedomintelligence/huatuogpt-3-27b/on/instinct-mi50