# Can the Apple M3 Ultra (512 GB) run Inkling-2-Small?

> Yes. The Apple M3 Ultra (512 GB) runs Inkling-2-Small fully in unified memory at Q6_K (about 311 GB of 384 GB), at roughly 1.4 tokens/s.

Apple M3 Ultra (512 GB): 512 GB (384 GB usable), 819 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 125.15 | fits | 3.6 |
| Q3_K_M | Noticeable loss | 185.09 | fits | 2.4 |
| Q4_K_M | Small loss | 229.1 | fits | 1.9 |
| Q5_K_M | Near-lossless | 268.44 | fits | 1.7 |
| Q6_K (pick) | Near-lossless | 310.58 | fits | 1.4 |
| Q8_0 | Lossless | 400.02 | no | — |
| F16 | Lossless | 475.68 | no | — |

## Run it

From the Ollama library (ollama):

```bash
ollama run inkling-2-small
```

UD-Q4_K_XL straight from Hugging Face (ollama):

```bash
ollama run hf.co/unsloth/Inkling-2-Small-GGUF:UD-Q4_K_XL
```

Ask about an image (transformers):

```python
from transformers import pipeline

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

- [zai-org/GLM-5.3-Flash](https://selfhost.directory/models/zai-org/glm-5.3-flash/on/apple-m3-ultra-512gb): Q8_0 ≈356.44 GB, est. 23 tok/s
- [MiniMaxAI/MiniMax-M3](https://selfhost.directory/models/minimaxai/minimax-m3/on/apple-m3-ultra-512gb): Q6_K ≈345.43 GB, est. 1.3 tok/s
- [Qwen/Qwen3.5-397B-A17B](https://selfhost.directory/models/qwen/qwen3.5-397b-a17b/on/apple-m3-ultra-512gb): Q6_K ≈320.82 GB, est. 32 tok/s
- [Qwen/Qwen3.8-Flash-Next](https://selfhost.directory/models/qwen/qwen3.8-flash-next/on/apple-m3-ultra-512gb): Q8_0 ≈185.32 GB, est. 6.9 tok/s
- [MiniMaxAI/MiniMax-M3.1-Flash](https://selfhost.directory/models/minimaxai/minimax-m3.1-flash/on/apple-m3-ultra-512gb): Q8_0 ≈3.49 GB, est. 1.9 tok/s
- [deepseek-ai/DeepSeek-V4-Flash-Vision-Exp](https://selfhost.directory/models/deepseek-ai/deepseek-v4-flash-vision-exp/on/apple-m3-ultra-512gb): Q8_0 ≈317.7 GB, est. 28 tok/s

---
Model: https://selfhost.directory/models/thinkingmachines/inkling-2-small. GPU: https://selfhost.directory/models/gpus/apple-m3-ultra-512gb. Source: https://selfhost.directory/models/thinkingmachines/inkling-2-small/on/apple-m3-ultra-512gb