# Can the RTX 4070 run Spark-X2.6-4B-Base?

> Yes. The RTX 4070 runs Spark-X2.6-4B-Base fully in VRAM at FP16 / BF16 (about 9.7 GB of 12 GB), at roughly 34 tokens/s.

GeForce RTX 4070: 12 GB (12 GB usable), 504 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 3.37 | fits | 205 |
| Q3_K_M | Noticeable loss | 3.75 | fits | 138 |
| Q4_K_M | Small loss | 4.17 | fits | 111 |
| Q5_K_M | Near-lossless | 4.54 | fits | 95 |
| Q6_K | Near-lossless | 4.94 | fits | 82 |
| Q8_0 | Lossless | 5.9 | fits | 63 |
| F16 (pick) | Lossless | 9.67 | fits | 34 |

## Run it

Q6_K straight from Hugging Face (ollama):

```bash
ollama run hf.co/mradermacher/Spark-X2.6-4B-Base-i1-GGUF:Q6_K
```

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

```bash
llama-server -hf mradermacher/Spark-X2.6-4B-Base-i1-GGUF:Q6_K
```

Download with the lms CLI (lmstudio):

```bash
lms get mradermacher/Spark-X2.6-4B-Base-i1-GGUF@Q6_K
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve XHToken/Spark-X2.6-4B-Base --host 0.0.0.0 --port 30000
```

Docker Compose (NVIDIA) (sglang):

```yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve XHToken/Spark-X2.6-4B-Base --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="XHToken/Spark-X2.6-4B-Base", 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

- [Qwen/Qwen3-4B](https://selfhost.directory/models/qwen/qwen3-4b/on/rtx-4070): Q8_0 ≈5.82 GB, est. 65 tok/s
- [meta-llama/Llama-3.2-3B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-3b-instruct/on/rtx-4070): Q8_0 ≈4.73 GB, est. 81 tok/s
- [microsoft/Phi-4-mini-instruct](https://selfhost.directory/models/microsoft/phi-4-mini-instruct/on/rtx-4070): Q8_0 ≈5.49 GB, est. 68 tok/s
- [XHToken/Spark-X2.6-4B](https://selfhost.directory/models/xhtoken/spark-x2.6-4b/on/rtx-4070): Q8_0 ≈5.9 GB, est. 63 tok/s
- [Qwen/Qwen3-4B-Instruct-2507](https://selfhost.directory/models/qwen/qwen3-4b-instruct-2507/on/rtx-4070): Q8_0 ≈5.82 GB, est. 65 tok/s
- [XHToken/Spark-X2.5-4B](https://selfhost.directory/models/xhtoken/spark-x2.5-4b/on/rtx-4070): Q8_0 ≈5.9 GB, est. 63 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/rtx-4060): Q8_0, est. 34 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/apple-m4-16gb): F16, est. 8 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/rx-6700-xt): F16, est. 26 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/rtx-3060): F16, est. 24 tok/s
- [Arc B580](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/arc-b580): F16, est. 30 tok/s
- [Tesla T4](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/tesla-t4): F16, est. 21 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/arc-a770): F16, est. 37 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/rx-7800-xt): F16, est. 42 tok/s

---
Model: https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base. GPU: https://selfhost.directory/models/gpus/rtx-4070. Source: https://selfhost.directory/models/xhtoken/spark-x2.6-4b-base/on/rtx-4070