# Can the Tesla P40 run ZwZ2-9B?

> Yes. The Tesla P40 runs ZwZ2-9B fully in VRAM at FP16 / BF16 (about 19 GB of 24 GB), at roughly 10 tokens/s.

Tesla P40: 24 GB (24 GB usable), 347 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 4.53 | fits | 62 |
| Q3_K_M | Noticeable loss | 6.03 | fits | 41 |
| Q4_K_M | Small loss | 7 | fits | 33 |
| Q5_K_M | Near-lossless | 7.82 | fits | 29 |
| Q6_K | Near-lossless | 8.69 | fits | 25 |
| Q8_0 | Lossless | 10.81 | fits | 19 |
| F16 (pick) | Lossless | 19.02 | fits | 10 |

## Run it

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

```bash
llama-server -hf inclusionAI/ZwZ2-9B-GGUF:F16
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve inclusionAI/ZwZ2-9B
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: inclusionAI/ZwZ2-9B
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve inclusionAI/ZwZ2-9B --host 0.0.0.0 --port 30000
```

Docker Compose (NVIDIA) (sglang):

```yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve inclusionAI/ZwZ2-9B --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]
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="inclusionAI/ZwZ2-9B", 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/tesla-p40): Q8_0 ≈10.81 GB, est. 19 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/tesla-p40): Q8_0 ≈10.15 GB, est. 20 tok/s
- [Qwen/Qwen2.5-VL-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-7b-instruct/on/tesla-p40): Q8_0 ≈8.86 GB, est. 22 tok/s
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b/on/tesla-p40): Q8_0 ≈10.83 GB, est. 19 tok/s
- [google/gemma-3-12b-it](https://selfhost.directory/models/google/gemma-3-12b-it/on/tesla-p40): Q8_0 ≈15.54 GB, est. 15 tok/s
- [Cloudflare/clef-flash](https://selfhost.directory/models/cloudflare/clef-flash/on/tesla-p40): Q8_0 ≈10.96 GB, est. 19 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/inclusionai/zwz2-9b/on/rtx-4060): Q4_K_M, est. 26 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/inclusionai/zwz2-9b/on/apple-m4-16gb): Q6_K, est. 8.5 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/inclusionai/zwz2-9b/on/rx-6700-xt): Q8_0, est. 21 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/inclusionai/zwz2-9b/on/rtx-3060): Q8_0, est. 20 tok/s
- [Arc B580](https://selfhost.directory/models/inclusionai/zwz2-9b/on/arc-b580): Q8_0, est. 25 tok/s
- [Tesla T4](https://selfhost.directory/models/inclusionai/zwz2-9b/on/tesla-t4): Q8_0, est. 18 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/inclusionai/zwz2-9b/on/arc-a770): Q8_0, est. 31 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/inclusionai/zwz2-9b/on/rx-7800-xt): Q8_0, est. 34 tok/s

---
Model: https://selfhost.directory/models/inclusionai/zwz2-9b. GPU: https://selfhost.directory/models/gpus/tesla-p40. Source: https://selfhost.directory/models/inclusionai/zwz2-9b/on/tesla-p40