# Can the RTX 4060 run KORMo-Web-11B?

> Yes, but only at Q3_K_M (about 7.1 GB of 8.0 GB), which costs noticeable quality, at roughly 27 tokens/s.

GeForce RTX 4060: 8 GB (8 GB usable), 272 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 5.35 | fits | 41 |
| Q3_K_M (pick) | Noticeable loss | 7.1 | fits | 27 |
| Q4_K_M | Small loss | 8.38 | offload | 19 |
| Q5_K_M | Near-lossless | 9.53 | offload | 12 |
| Q6_K | Near-lossless | 10.76 | offload | 8.5 |
| Q8_0 | Lossless | 13.38 | offload | 5.2 |
| F16 | Lossless | 23.64 | offload | 2 |

## Run it

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve KORMo-VL/KORMo-Web-11B
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: KORMo-VL/KORMo-Web-11B
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="KORMo-VL/KORMo-Web-11B", 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/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b/on/rtx-4060): Q4_K_M ≈7.05 GB, est. 26 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/rtx-4060): Q5_K_M ≈7.35 GB, est. 24 tok/s
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b/on/rtx-4060): Q4_K_M ≈7.21 GB, est. 26 tok/s
- [Qwen/Qwen2.5-VL-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-7b-instruct/on/rtx-4060): Q6_K ≈7.05 GB, est. 22 tok/s
- [zai-org/GLM-4.6V-Flash](https://selfhost.directory/models/zai-org/glm-4.6v-flash/on/rtx-4060): Q4_K_M ≈6.84 GB, est. 24 tok/s
- [Cloudflare/clef-flash](https://selfhost.directory/models/cloudflare/clef-flash/on/rtx-4060): Q4_K_M ≈7.41 GB, est. 26 tok/s

## Other GPUs that run it

- [Apple M4 (16 GB)](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/apple-m4-16gb): Q5_K_M, est. 8.3 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/rx-6700-xt): Q6_K, est. 23 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/rtx-3060): Q6_K, est. 21 tok/s
- [Arc B580](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/arc-b580): Q6_K, est. 27 tok/s
- [Tesla T4](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/tesla-t4): Q8_0, est. 15 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/arc-a770): Q8_0, est. 26 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/rx-7800-xt): Q8_0, est. 29 tok/s
- [Tesla P40](https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/tesla-p40): Q8_0, est. 16 tok/s

---
Model: https://selfhost.directory/models/kormo-vl/kormo-web-11b. GPU: https://selfhost.directory/models/gpus/rtx-4060. Source: https://selfhost.directory/models/kormo-vl/kormo-web-11b/on/rtx-4060