# Can the Tesla T4 run LBS-27B?

> 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 | 12.85 | fits | 20 |
| Q3_K_M (pick) | Noticeable loss | 15.37 | tight | 13 |
| Q4_K_M | Small loss | 19.32 | offload | 6.2 |
| Q5_K_M | Near-lossless | 22.72 | offload | 4 |
| Q6_K | Near-lossless | 25.6 | offload | 3 |
| Q8_0 | Lossless | 30.54 | offload | 2 |
| F16 | Lossless | 55.12 | no | — |

## Run it

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

```bash
llama-server -hf bartowski/LBS-27B-GGUF:Q3_K_M
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve inclusionAI/LBS-27B
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: inclusionAI/LBS-27B
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve inclusionAI/LBS-27B --host 0.0.0.0 --port 30000
```

Docker Compose (NVIDIA) (sglang):

```yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve inclusionAI/LBS-27B --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```


## Vision models that fit comfortably

- [google/gemma-3-12b-it](https://selfhost.directory/models/google/gemma-3-12b-it/on/tesla-t4): Q6_K ≈12.76 GB, est. 18 tok/s
- [GrootTeam/Groot-19B-A3B-261023](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/tesla-t4): Q4_K_M ≈13.34 GB, est. 97 tok/s
- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b/on/tesla-t4): Q8_0 ≈10.81 GB, est. 17 tok/s
- [google/translategemma-12b-it](https://selfhost.directory/models/google/translategemma-12b-it/on/tesla-t4): Q6_K ≈12.95 GB, est. 16 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/tesla-t4): Q8_0 ≈10.15 GB, est. 19 tok/s
- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-11b-vision-instruct/on/tesla-t4): Q8_0 ≈11.91 GB, est. 16 tok/s

## Other GPUs that run it

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

---
Model: https://selfhost.directory/models/inclusionai/lbs-27b. GPU: https://selfhost.directory/models/gpus/tesla-t4. Source: https://selfhost.directory/models/inclusionai/lbs-27b/on/tesla-t4