# Can the RTX 4070 run Cola2?

> Yes. The RTX 4070 runs Cola2 fully in VRAM at Q8_0 (about 11 GB of 12 GB), at roughly 30 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 | 4.39 | fits | 96 |
| Q3_K_M | Noticeable loss | 5.76 | fits | 65 |
| Q4_K_M | Small loss | 6.77 | fits | 52 |
| Q5_K_M | Near-lossless | 7.67 | fits | 44 |
| Q6_K | Near-lossless | 8.63 | fits | 38 |
| Q8_0 (pick) | Lossless | 10.68 | fits | 30 |
| F16 | Lossless | 18.72 | offload | 4.3 |

## Run it

Chat with the pipeline API (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-generation", model="ByteDance-Seed/Cola2", 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/Qwen3-8B](https://selfhost.directory/models/qwen/qwen3-8b/on/rtx-4070): Q8_0 ≈10.15 GB, est. 32 tok/s
- [meta-llama/Llama-3.1-8B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.1-8b-instruct/on/rtx-4070): Q8_0 ≈9.84 GB, est. 32 tok/s
- [meta-llama/Meta-Llama-3-8B-Instruct](https://selfhost.directory/models/meta-llama/meta-llama-3-8b-instruct/on/rtx-4070): Q8_0 ≈9.85 GB, est. 32 tok/s
- [Qwen/Qwen2.5-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-7b-instruct/on/rtx-4070): Q8_0 ≈8.86 GB, est. 34 tok/s
- [xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/rtx-4070): Q8_0 ≈11.07 GB, est. 28 tok/s
- [google/gemma-2-9b-it](https://selfhost.directory/models/google/gemma-2-9b-it/on/rtx-4070): Q6_K ≈10.55 GB, est. 36 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/bytedance-seed/cola2/on/rtx-4060): Q4_K_M, est. 28 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/bytedance-seed/cola2/on/apple-m4-16gb): Q6_K, est. 9.1 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/bytedance-seed/cola2/on/rx-6700-xt): Q8_0, est. 23 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/bytedance-seed/cola2/on/rtx-3060): Q8_0, est. 21 tok/s
- [Arc B580](https://selfhost.directory/models/bytedance-seed/cola2/on/arc-b580): Q8_0, est. 27 tok/s
- [Tesla T4](https://selfhost.directory/models/bytedance-seed/cola2/on/tesla-t4): Q8_0, est. 19 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/bytedance-seed/cola2/on/arc-a770): Q8_0, est. 33 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/bytedance-seed/cola2/on/rx-7800-xt): Q8_0, est. 37 tok/s

---
Model: https://selfhost.directory/models/bytedance-seed/cola2. GPU: https://selfhost.directory/models/gpus/rtx-4070. Source: https://selfhost.directory/models/bytedance-seed/cola2/on/rtx-4070