# Can the RTX A4000 run Inkling-2-Mini?

> Yes. The RTX A4000 runs Inkling-2-Mini fully in VRAM at FP16 / BF16 (about 1.9 GB of 16 GB), at roughly 36 tokens/s.

RTX A4000: 16 GB (16 GB usable), 448 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 9.73 | fits | 217 |
| Q3_K_M | Noticeable loss | 13.86 | fits | 146 |
| Q4_K_M | Small loss | 16.89 | offload | 88 |
| Q5_K_M | Near-lossless | 19.6 | offload | 46 |
| Q6_K | Near-lossless | 22.51 | offload | 30 |
| Q8_0 | Lossless | 1.64 | fits | 67 |
| 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
```

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/rtx-a4000): Q6_K ≈12.76 GB, est. 25 tok/s
- [GrootTeam/Groot-19B-A3B-261023](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/rtx-a4000): Q4_K_M ≈13.34 GB, est. 135 tok/s
- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b/on/rtx-a4000): Q8_0 ≈10.81 GB, est. 24 tok/s
- [google/translategemma-12b-it](https://selfhost.directory/models/google/translategemma-12b-it/on/rtx-a4000): Q6_K ≈12.95 GB, est. 23 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/rtx-a4000): Q8_0 ≈10.15 GB, est. 26 tok/s
- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-11b-vision-instruct/on/rtx-a4000): Q8_0 ≈11.91 GB, est. 22 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
- [Arc B580](https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/arc-b580): F16, est. 36 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

---
Model: https://selfhost.directory/models/thinkingmachines/inkling-2-mini. GPU: https://selfhost.directory/models/gpus/rtx-a4000. Source: https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/rtx-a4000