# Can the Tesla T4 run Hemmingway-1.5?

> Just about. At Q3_K_M it needs about 16 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 | 13.08 | fits | 20 |
| Q3_K_M (pick) | Noticeable loss | 15.6 | tight | 13 |
| Q4_K_M | Small loss | 19.55 | offload | 6 |
| Q5_K_M | Near-lossless | 22.96 | offload | 4 |
| Q6_K | Near-lossless | 25.83 | offload | 3 |
| Q8_0 | Lossless | 30.98 | offload | 2 |
| F16 | Lossless | 55.95 | no | — |

## Run it

Q3_K_M straight from Hugging Face (ollama):

```bash
ollama run hf.co/bartowski/HemmingwayAI_Hemmingway-1.5-GGUF:Q3_K_M
```

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

```bash
llama-server -hf bartowski/HemmingwayAI_Hemmingway-1.5-GGUF:Q3_K_M
```

Download with the lms CLI (lmstudio):

```bash
lms get bartowski/HemmingwayAI_Hemmingway-1.5-GGUF@Q3_K_M
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve HemmingwayAI/Hemmingway-1.5
```

Smaller AWQ build (vllm):

```bash
vllm serve cyankiwi/Hemmingway-1.5-AWQ-INT4
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: HemmingwayAI/Hemmingway-1.5
    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 HemmingwayAI/Hemmingway-1.5 --host 0.0.0.0 --port 30000
```

Docker Compose (NVIDIA) (sglang):

```yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve HemmingwayAI/Hemmingway-1.5 --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]
```

Chat with the pipeline API (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-generation", model="HemmingwayAI/Hemmingway-1.5", 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/hemmingwayai/hemmingway-1.5/on/rtx-a4000): Q3_K_M, est. 19 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/arc-a770): Q3_K_M, est. 23 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/rx-7800-xt): Q3_K_M, est. 26 tok/s
- [Tesla P40](https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/tesla-p40): Q4_K_M, est. 12 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/rx-7900-xtx): Q4_K_M, est. 32 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/instinct-mi50): Q6_K, est. 25 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/rtx-5090): Q6_K, est. 44 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/apple-m4-pro-48gb): Q8_0, est. 5.3 tok/s

---
Model: https://selfhost.directory/models/hemmingwayai/hemmingway-1.5. GPU: https://selfhost.directory/models/gpus/tesla-t4. Source: https://selfhost.directory/models/hemmingwayai/hemmingway-1.5/on/tesla-t4