# Can the Tesla P40 run Inkling-2-Mini?

> Yes. The Tesla P40 runs Inkling-2-Mini fully in VRAM at FP16 / BF16 (about 1.9 GB of 24 GB), at roughly 28 tokens/s.

Tesla P40: 24 GB (24 GB usable), 347 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 9.73 | fits | 168 |
| Q3_K_M | Noticeable loss | 13.86 | fits | 113 |
| Q4_K_M | Small loss | 16.89 | fits | 91 |
| Q5_K_M | Near-lossless | 19.6 | fits | 78 |
| Q6_K | Near-lossless | 22.51 | fits | 67 |
| Q8_0 | Lossless | 1.64 | fits | 52 |
| F16 (pick) | Lossless | 1.88 | fits | 28 |

## 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

- [Qwen/Qwen3.8-27B](https://selfhost.directory/models/qwen/qwen3.8-27b/on/tesla-p40): Q5_K_M ≈21.82 GB, est. 9.7 tok/s
- [google/gemma-4-26B-A4B-it](https://selfhost.directory/models/google/gemma-4-26b-a4b-it/on/tesla-p40): Q5_K_M ≈20.32 GB, est. 67 tok/s
- [Qwen/Qwen3.6-27B](https://selfhost.directory/models/qwen/qwen3.6-27b/on/tesla-p40): Q5_K_M ≈21.58 GB, est. 9.7 tok/s
- [google/gemma-3-27b-it](https://selfhost.directory/models/google/gemma-3-27b-it/on/tesla-p40): Q4_K_M ≈20.56 GB, est. 11 tok/s
- [Qwen/Qwen3.5-27B](https://selfhost.directory/models/qwen/qwen3.5-27b/on/tesla-p40): Q5_K_M ≈21.67 GB, est. 9.7 tok/s
- [meta-models/Muse-Glimmer-30B](https://selfhost.directory/models/meta-models/muse-glimmer-30b/on/tesla-p40): Q5_K_M ≈21.62 GB, est. 9 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/tesla-p40. Source: https://selfhost.directory/models/thinkingmachines/inkling-2-mini/on/tesla-p40