# Can the Arc A380 run ZwZ2-4B?

> Yes. The Arc A380 runs ZwZ2-4B fully in VRAM at Q6_K (about 5.1 GB of 6.0 GB), at roughly 27 tokens/s.

Arc A380: 6 GB (6 GB usable), 186 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 3.19 | fits | 69 |
| Q3_K_M | Noticeable loss | 3.53 | fits | 46 |
| Q4_K_M | Small loss | 4.15 | fits | 37 |
| Q5_K_M | Near-lossless | 4.72 | fits | 32 |
| Q6_K (pick) | Near-lossless | 5.11 | fits | 27 |
| Q8_0 | Lossless | 5.88 | tight | 21 |
| F16 | Lossless | 9.74 | offload | 6.2 |

## Run it

Q6_K straight from Hugging Face (ollama):

```bash
ollama run hf.co/bartowski/ZwZ2-4B-GGUF:Q6_K
```

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

```bash
llama-server -hf bartowski/ZwZ2-4B-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 bartowski/ZwZ2-4B-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99
```

Download with the lms CLI (lmstudio):

```bash
lms get bartowski/ZwZ2-4B-GGUF@Q6_K
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="inclusionAI/ZwZ2-4B", 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/Qwen3.5-4B](https://selfhost.directory/models/qwen/qwen3.5-4b/on/arc-a380): Q6_K ≈4.94 GB, est. 27 tok/s
- [google/gemma-3-4b-it](https://selfhost.directory/models/google/gemma-3-4b-it/on/arc-a380): Q8_0 ≈5.2 GB, est. 22 tok/s
- [Qwen/Qwen3-VL-4B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-4b-instruct/on/arc-a380): Q6_K ≈4.86 GB, est. 28 tok/s
- [google/medgemma-1.5-4b-it](https://selfhost.directory/models/google/medgemma-1.5-4b-it/on/arc-a380): Q8_0 ≈5.6 GB, est. 22 tok/s
- [google/medgemma-4b-it](https://selfhost.directory/models/google/medgemma-4b-it/on/arc-a380): Q8_0 ≈5.6 GB, est. 22 tok/s
- [google/translategemma-4b-it](https://selfhost.directory/models/google/translategemma-4b-it/on/arc-a380): Q8_0 ≈5.6 GB, est. 19 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/inclusionai/zwz2-4b/on/rtx-4060): Q8_0, est. 31 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/inclusionai/zwz2-4b/on/apple-m4-16gb): F16, est. 7.3 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/inclusionai/zwz2-4b/on/rx-6700-xt): F16, est. 23 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/inclusionai/zwz2-4b/on/rtx-3060): F16, est. 22 tok/s
- [Arc B580](https://selfhost.directory/models/inclusionai/zwz2-4b/on/arc-b580): F16, est. 28 tok/s
- [Tesla T4](https://selfhost.directory/models/inclusionai/zwz2-4b/on/tesla-t4): F16, est. 19 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/inclusionai/zwz2-4b/on/arc-a770): F16, est. 34 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/inclusionai/zwz2-4b/on/rx-7800-xt): F16, est. 38 tok/s

---
Model: https://selfhost.directory/models/inclusionai/zwz2-4b. GPU: https://selfhost.directory/models/gpus/arc-a380. Source: https://selfhost.directory/models/inclusionai/zwz2-4b/on/arc-a380