# Can the Arc A580 run DeskForge-Gemma4-E4B?

> Yes. The Arc A580 runs DeskForge-Gemma4-E4B fully in VRAM at Q6_K (about 7.2 GB of 8.0 GB), at roughly 43 tokens/s.

Arc A580: 8 GB (8 GB usable), 512 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 5.44 | fits | 108 |
| Q3_K_M | Noticeable loss | 5.87 | fits | 73 |
| Q4_K_M | Small loss | 6.35 | fits | 58 |
| Q5_K_M | Near-lossless | 6.76 | fits | 50 |
| Q6_K (pick) | Near-lossless | 7.2 | fits | 43 |
| Q8_0 | Lossless | 8.96 | offload | 18 |
| F16 | Lossless | 15.78 | offload | 3.8 |

## Run it

Q6_K straight from Hugging Face (ollama):

```bash
ollama run hf.co/mradermacher/DeskForge-Gemma4-E4B-GGUF:Q6_K
```

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

```bash
llama-server -hf mradermacher/DeskForge-Gemma4-E4B-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/DeskForge-Gemma4-E4B-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99
```

Download with the lms CLI (lmstudio):

```bash
lms get mradermacher/DeskForge-Gemma4-E4B-GGUF@Q6_K
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="docling-project/DeskForge-Gemma4-E4B", 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/Qwen2.5-VL-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-7b-instruct/on/arc-a580): Q6_K ≈7.05 GB, est. 41 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/arc-a580): Q5_K_M ≈7.35 GB, est. 45 tok/s
- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b/on/arc-a580): Q4_K_M ≈7.05 GB, est. 48 tok/s
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b/on/arc-a580): Q4_K_M ≈7.21 GB, est. 49 tok/s
- [openbmb/MiniCPM-V-4_5](https://selfhost.directory/models/openbmb/minicpm-v-4_5/on/arc-a580): Q5_K_M ≈7.35 GB, est. 46 tok/s
- [ByteDance-Seed/UI-TARS-1.5-7B](https://selfhost.directory/models/bytedance-seed/ui-tars-1.5-7b/on/arc-a580): Q6_K ≈7.05 GB, est. 41 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/rtx-4060): Q6_K, est. 23 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/apple-m4-16gb): Q8_0, est. 7.8 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/rx-6700-xt): Q8_0, est. 25 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/rtx-3060): Q8_0, est. 23 tok/s
- [Arc B580](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/arc-b580): Q8_0, est. 30 tok/s
- [Tesla T4](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/tesla-t4): Q8_0, est. 21 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/arc-a770): Q8_0, est. 37 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/rx-7800-xt): Q8_0, est. 41 tok/s

---
Model: https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b. GPU: https://selfhost.directory/models/gpus/arc-a580. Source: https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/arc-a580