# Can the Tesla P40 run Qwen3.8-27B-DSpine-b16?

> Yes. The Tesla P40 runs Qwen3.8-27B-DSpine-b16 fully in VRAM at FP16 / BF16 (about 4.6 GB of 24 GB), at roughly 47 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 | 1.31 | fits | 287 |
| Q3_K_M | Noticeable loss | 1.62 | fits | 193 |
| Q4_K_M | Small loss | 1.89 | fits | 155 |
| Q5_K_M | Near-lossless | 2.07 | fits | 132 |
| Q6_K | Near-lossless | 2.29 | fits | 114 |
| Q8_0 | Lossless | 2.81 | fits | 89 |
| F16 (pick) | Lossless | 4.63 | fits | 47 |

## Chat models that fit comfortably

- [LiquidAI/LFM3-1.7B](https://selfhost.directory/models/liquidai/lfm3-1.7b/on/tesla-p40): Q8_0 ≈2.69 GB, est. 104 tok/s
- [Qwen/Qwen3-1.7B](https://selfhost.directory/models/qwen/qwen3-1.7b/on/tesla-p40): Q8_0 ≈3.18 GB, est. 88 tok/s
- [Qwen/Qwen2.5-1.5B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-1.5b-instruct/on/tesla-p40): Q8_0 ≈2.57 GB, est. 116 tok/s
- [meta-llama/Llama-3.2-3B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-3b-instruct/on/tesla-p40): Q8_0 ≈4.73 GB, est. 56 tok/s
- [openbmb/MiniCPM5-2B](https://selfhost.directory/models/openbmb/minicpm5-2b/on/tesla-p40): Q8_0 ≈3.46 GB, est. 71 tok/s
- [google/gemma-2-2b-it](https://selfhost.directory/models/google/gemma-2-2b-it/on/tesla-p40): Q8_0 ≈4.03 GB, est. 69 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/rtx-4060): F16, est. 37 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/apple-m4-16gb): F16, est. 16 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/rx-6700-xt): F16, est. 52 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/rtx-3060): F16, est. 49 tok/s
- [Arc B580](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/arc-b580): F16, est. 62 tok/s
- [Tesla T4](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/tesla-t4): F16, est. 43 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/arc-a770): F16, est. 76 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/rx-7800-xt): F16, est. 85 tok/s

---
Model: https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16. GPU: https://selfhost.directory/models/gpus/tesla-p40. Source: https://selfhost.directory/models/tencent/qwen3.8-27b-dspine-b16/on/tesla-p40