# Can the Tesla T4 run Qwen3.8-27B-Longbook27-v2?

> Just about. At Q3_K_M it needs about 15 GB of the 16 GB available, so keep the context short, at roughly 13 tokens/s.

Tesla T4: 16 GB (16 GB usable), 320 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 11.2 | fits | 20 |
| Q3_K_M (pick) | Noticeable loss | 15.44 | tight | 13 |
| Q4_K_M | Small loss | 18.55 | offload | 6.7 |
| Q5_K_M | Near-lossless | 21.33 | offload | 4.4 |
| Q6_K | Near-lossless | 24.31 | offload | 3.2 |
| Q8_0 | Lossless | 30.63 | offload | 2 |
| F16 | Lossless | 55.45 | no | — |

## Run it

Chat with the pipeline API (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-generation", model="summerAIO/Qwen3.8-27B-Longbook27-v2", 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

- [openai/gpt-oss-20b](https://selfhost.directory/models/openai/gpt-oss-20b/on/tesla-t4): Q8_0 ≈12.72 GB, est. 40 tok/s
- [Qwen/Qwen3-14B](https://selfhost.directory/models/qwen/qwen3-14b/on/tesla-t4): Q6_K ≈13.6 GB, est. 14 tok/s
- [microsoft/phi-4](https://selfhost.directory/models/microsoft/phi-4/on/tesla-t4): Q6_K ≈13.82 GB, est. 15 tok/s
- [Qwen/Qwen2.5-14B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-14b-instruct/on/tesla-t4): Q6_K ≈13.85 GB, est. 14 tok/s
- [Qwen/Qwen3-8B](https://selfhost.directory/models/qwen/qwen3-8b/on/tesla-t4): Q8_0 ≈10.15 GB, est. 20 tok/s
- [meta-llama/Llama-3.1-8B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.1-8b-instruct/on/tesla-t4): Q8_0 ≈9.84 GB, est. 21 tok/s

## Other GPUs that run it

- [RTX A4000](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/rtx-a4000): Q3_K_M, est. 19 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/arc-a770): Q3_K_M, est. 23 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/rx-7800-xt): Q3_K_M, est. 26 tok/s
- [Tesla P40](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/tesla-p40): Q5_K_M, est. 9.9 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/rx-7900-xtx): Q5_K_M, est. 27 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/instinct-mi50): Q6_K, est. 25 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/rtx-5090): Q6_K, est. 44 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/apple-m4-pro-48gb): Q8_0, est. 5.2 tok/s

---
Model: https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2. GPU: https://selfhost.directory/models/gpus/tesla-t4. Source: https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/tesla-t4