# Can the RTX 4060 run plamo-3-translate-8b?

> Yes. The RTX 4060 runs plamo-3-translate-8b fully in VRAM at Q4_K_M (about 6.4 GB of 8.0 GB).

GeForce RTX 4060: 8 GB (8 GB usable), 272 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q4_K_M (pick) | Small loss | 6.4 | fits | — |
| Q8_0 | Lossless | 10.63 | no | — |
| F16 | Lossless | 19.57 | no | — |

## Run it

Q4_K_M straight from Hugging Face (ollama):

```bash
ollama run hf.co/pfnet/plamo-3-translate-8b-GGUF:Q4_K_M
```

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

```bash
llama-server -hf pfnet/plamo-3-translate-8b-GGUF:Q4_K_M
```

Download with the lms CLI (lmstudio):

```bash
lms get pfnet/plamo-3-translate-8b-GGUF@Q4_K_M
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve pfnet/plamo-3-translate-8b
```

Smaller FP8 build (vllm):

```bash
vllm serve pfnet/plamo-3-translate-8b-FP8
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: pfnet/plamo-3-translate-8b
    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-8b")
result = pipe("Self-hosting puts you in control of your data.")
print(result)
```


## Translation models that fit comfortably

- [sarvamai/sarvam-translate](https://selfhost.directory/models/sarvamai/sarvam-translate/on/rtx-4060): Q8_0 ≈5.61 GB
- [ModelSpace/GemmaX2-28-2B-v0.1](https://selfhost.directory/models/modelspace/gemmax2-28-2b-v0.1/on/rtx-4060): Q8_0 ≈4.3 GB
- [IndexTeam/Index-Translate-2B](https://selfhost.directory/models/indexteam/index-translate-2b/on/rtx-4060): F16 ≈5.58 GB
- [tencent/Hy-MT2-1.8B](https://selfhost.directory/models/tencent/hy-mt2-1.8b/on/rtx-4060): F16 ≈5.06 GB
- [tencent/HY-MT1.5-1.8B](https://selfhost.directory/models/tencent/hy-mt1.5-1.8b/on/rtx-4060): F16 ≈5.06 GB
- [kyutai/hibiki-2b-pytorch-bf16](https://selfhost.directory/models/kyutai/hibiki-2b-pytorch-bf16/on/rtx-4060): F16 ≈4.97 GB

## Other GPUs that run it

- [Apple M4 (16 GB)](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/apple-m4-16gb): Q4_K_M
- [Radeon RX 6700 XT](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/rx-6700-xt): Q8_0
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/rtx-3060): Q8_0
- [Arc B580](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/arc-b580): Q8_0
- [Tesla T4](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/tesla-t4): Q8_0
- [Arc A770 16GB](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/arc-a770): Q8_0
- [Radeon RX 7800 XT](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/rx-7800-xt): Q8_0
- [Tesla P40](https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/tesla-p40): F16

---
Model: https://selfhost.directory/models/pfnet/plamo-3-translate-8b. GPU: https://selfhost.directory/models/gpus/rtx-4060. Source: https://selfhost.directory/models/pfnet/plamo-3-translate-8b/on/rtx-4060