# Can the Arc B580 run Inkling-2-Mini?

> Yes. The Arc B580 runs Inkling-2-Mini fully in VRAM at FP16 / BF16 (about 1.9 GB of 12 GB), at roughly 36 tokens/s.

Arc B580: 12 GB (12 GB usable), 456 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 9.73 | fits | 221 |
| Q3_K_M | Noticeable loss | 13.86 | offload | 79 |
| Q4_K_M | Small loss | 16.89 | offload | 41 |
| Q5_K_M | Near-lossless | 19.6 | offload | 29 |
| Q6_K | Near-lossless | 22.51 | offload | 22 |
| Q8_0 | Lossless | 1.64 | fits | 68 |
| F16 (pick) | Lossless | 1.88 | fits | 36 |

## Run it

From the Ollama library (ollama):

```bash
ollama run inkling-2-mini
```

BF16 straight from Hugging Face (ollama):

```bash
ollama run hf.co/unsloth/Inkling-2-Mini-GGUF:BF16
```

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

```bash
llama-server -hf unsloth/Inkling-2-Mini-GGUF:BF16
```

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 unsloth/Inkling-2-Mini-GGUF:BF16 --host 0.0.0.0 --port 8080 -ngl 99
```

Download with the lms CLI (lmstudio):

```bash
lms get unsloth/Inkling-2-Mini-GGUF@BF16
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="thinkingmachines/Inkling-2-Mini", 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

- [google/gemma-3-12b-it](https://selfhost.directory/models/google/gemma-3-12b-it/on/arc-b580): Q4_K_M ≈10.45 GB, est. 34 tok/s
- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b/on/arc-b580): Q8_0 ≈10.81 GB, est. 24 tok/s
- [google/translategemma-12b-it](https://selfhost.directory/models/google/translategemma-12b-it/on/arc-b580): Q4_K_M ≈10.64 GB, est. 31 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/arc-b580): Q8_0 ≈10.15 GB, est. 27 tok/s
- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-11b-vision-instruct/on/arc-b580): Q6_K ≈10.35 GB, est. 29 tok/s
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b/on/arc-b580): Q8_0 ≈10.83 GB, est. 25 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/rtx-4060): F16, est. 22 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/apple-m4-16gb): F16, est. 9.5 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/rx-6700-xt): F16, est. 31 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/rtx-3060): F16, est. 29 tok/s
- [Tesla T4](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/tesla-t4): F16, est. 25 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/arc-a770): F16, est. 45 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/rx-7800-xt): F16, est. 50 tok/s
- [Tesla P40](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/tesla-p40): F16, est. 28 tok/s

---
Model: https://selfhost.directory/models/thinkingmachines/inkling-2-mini. GPU: https://selfhost.directory/models/gpus/arc-b580. Source: https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/arc-b580