# Can the Tesla P40 run RWKV7-G1k-13.3B-20260930?

> Yes. The Tesla P40 runs RWKV7-G1k-13.3B-20260930 fully in VRAM at Q8_0 (about 22 GB of 24 GB), at roughly 14 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 | 12.39 | fits | 44 |
| Q3_K_M | Noticeable loss | 14.47 | fits | 29 |
| Q4_K_M | Small loss | 15.99 | fits | 24 |
| Q5_K_M | Near-lossless | 17.35 | fits | 20 |
| Q6_K | Near-lossless | 18.81 | fits | 17 |
| Q8_0 (pick) | Lossless | 21.91 | fits | 14 |
| F16 | Lossless | 34.08 | offload | 3 |

## Run it

Chat with the pipeline API (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-generation", model="RWKV/RWKV7-G1k-13.3B-20260930", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])
```


## Chat models that fit comfortably

- [Qwen/Qwen3-14B](https://selfhost.directory/models/qwen/qwen3-14b/on/tesla-p40): Q8_0 ≈17.1 GB, est. 12 tok/s
- [microsoft/phi-4](https://selfhost.directory/models/microsoft/phi-4/on/tesla-p40): Q8_0 ≈17.3 GB, est. 12 tok/s
- [openai/gpt-oss-20b](https://selfhost.directory/models/openai/gpt-oss-20b/on/tesla-p40): Q8_0 ≈12.72 GB, est. 43 tok/s
- [Qwen/Qwen3-8B](https://selfhost.directory/models/qwen/qwen3-8b/on/tesla-p40): Q8_0 ≈10.15 GB, est. 22 tok/s
- [meta-llama/Llama-3.1-8B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.1-8b-instruct/on/tesla-p40): Q8_0 ≈9.84 GB, est. 22 tok/s
- [xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/tesla-p40): Q8_0 ≈11.07 GB, est. 19 tok/s

## Other GPUs that run it

- [Tesla T4](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/tesla-t4): Q3_K_M, est. 27 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/arc-a770): Q3_K_M, est. 47 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/rx-7800-xt): Q3_K_M, est. 53 tok/s
- [GeForce RTX 3090](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/rtx-3090): Q8_0, est. 37 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/rx-7900-xtx): Q8_0, est. 37 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/instinct-mi50): Q8_0, est. 40 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/rtx-5090): Q8_0, est. 70 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/apple-m4-pro-48gb): F16, est. 5.7 tok/s

---
Model: https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930. GPU: https://selfhost.directory/models/gpus/tesla-p40. Source: https://selfhost.directory/models/rwkv/rwkv7-g1k-13.3b-20260930/on/tesla-p40