# Can the Tesla P40 run plamo-3-translate-31b?

> Yes. The Tesla P40 runs plamo-3-translate-31b fully in VRAM at Q4_K_M (about 22 GB of 24 GB).

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

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q4_K_M (pick) | Small loss | 22.33 | fits | — |
| Q8_0 | Lossless | 38.21 | no | — |
| F16 | Lossless | 71.48 | no | — |

## Run it

Q4_K_M straight from Hugging Face (ollama):

```bash
ollama run hf.co/pfnet/plamo-3-translate-31b-GGUF:Q4_K_M
```

OpenAI-compatible server with a web UI (llama.cpp):

```bash
llama-server -hf pfnet/plamo-3-translate-31b-GGUF:Q4_K_M
```

Download with the lms CLI (lmstudio):

```bash
lms get pfnet/plamo-3-translate-31b-GGUF@Q4_K_M
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve pfnet/plamo-3-translate-31b
```

Smaller FP8 build (vllm):

```bash
vllm serve pfnet/plamo-3-translate-31b-FP8
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: pfnet/plamo-3-translate-31b
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Run with the translation pipeline (transformers):

```python
from transformers import pipeline

pipe = pipeline("translation", model="pfnet/plamo-3-translate-31b")
result = pipe("Self-hosting puts you in control of your data.")
print(result)
```


## Translation models that fit comfortably

- [IndexTeam/Index-Translate-9B](https://selfhost.directory/models/indexteam/index-translate-9b/on/tesla-p40): F16 ≈22.08 GB
- [tencent/Hy-MT2-7B](https://selfhost.directory/models/tencent/hy-mt2-7b/on/tesla-p40): F16 ≈18.45 GB
- [ModelSpace/GemmaX2-28-9B-v0.1](https://selfhost.directory/models/modelspace/gemmax2-28-9b-v0.1/on/tesla-p40): Q8_0 ≈12.56 GB
- [tencent/Hunyuan-MT-7B](https://selfhost.directory/models/tencent/hunyuan-mt-7b/on/tesla-p40): F16 ≈18.45 GB
- [pfnet/plamo-3-translate-8b](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/tesla-p40): F16 ≈19.57 GB
- [pfnet/plamo-2-translate](https://selfhost.directory/models/pfnet/plamo-2-translate/on/tesla-p40): F16 ≈21.8 GB

## Other GPUs that run it

- [GeForce RTX 3090](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/rtx-3090): Q4_K_M
- [Radeon RX 7900 XTX](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/rx-7900-xtx): Q4_K_M
- [Instinct MI50 32GB](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/instinct-mi50): Q4_K_M
- [GeForce RTX 5090](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/rtx-5090): Q4_K_M
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/apple-m4-pro-48gb): Q4_K_M
- [RTX A6000](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/rtx-a6000): Q8_0
- [Apple M1 Max (64 GB)](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/apple-m1-max-64gb): Q8_0
- [NVIDIA A100 80GB](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/a100-80gb): F16

---
Model: https://selfhost.directory/models/pfnet/plamo-3-translate-31b. GPU: https://selfhost.directory/models/gpus/tesla-p40. Source: https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/tesla-p40