# Can the Radeon RX 7800 XT run WeVisCut?

> Yes. The Radeon RX 7800 XT runs WeVisCut fully in VRAM at Q8_0 (about 11 GB of 16 GB), at roughly 34 tokens/s.

Radeon RX 7800 XT: 16 GB (16 GB usable), 624 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 4.53 | fits | 111 |
| Q3_K_M | Noticeable loss | 6.03 | fits | 75 |
| Q4_K_M | Small loss | 7 | fits | 60 |
| Q5_K_M | Near-lossless | 7.82 | fits | 51 |
| Q6_K | Near-lossless | 8.69 | fits | 44 |
| Q8_0 (pick) | Lossless | 10.81 | fits | 34 |
| F16 | Lossless | 19.02 | offload | 7.3 |

## Run it

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

```bash
llama-server -hf prithivMLmods/tencent-WeVisCut-GGUF:Q8_0
```

Docker with ROCm (AMD) (llama.cpp):

```bash
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-rocm \
  -hf prithivMLmods/tencent-WeVisCut-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve tencent/WeVisCut
```

Docker Compose (AMD ROCm) (vllm):

```yaml
services:
  vllm:
    image: rocm/vllm:latest
    command: vllm serve tencent/WeVisCut --host 0.0.0.0 --port 8000
    ports:
      - "8000:8000"
    ipc: host
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
    security_opt:
      - seccomp=unconfined
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve tencent/WeVisCut --host 0.0.0.0 --port 30000
```


## Omni models that fit comfortably

- [openbmb/MiniCPM-o-4_5](https://selfhost.directory/models/openbmb/minicpm-o-4_5/on/rx-7800-xt): Q8_0 ≈10.15 GB, est. 34 tok/s
- [google/gemma-4-E4B-it](https://selfhost.directory/models/google/gemma-4-e4b-it/on/rx-7800-xt): Q8_0 ≈9.17 GB, est. 40 tok/s
- [Qwen/Qwen2.5-Omni-7B](https://selfhost.directory/models/qwen/qwen2.5-omni-7b/on/rx-7800-xt): Q8_0 ≈8.86 GB, est. 30 tok/s
- [OpenMOSS-Team/MOSS-Music-8B-Instruct](https://selfhost.directory/models/openmoss-team/moss-music-8b-instruct/on/rx-7800-xt): Q8_0 ≈10.15 GB, est. 36 tok/s
- [google/gemma-4-12B-it](https://selfhost.directory/models/google/gemma-4-12b-it/on/rx-7800-xt): Q6_K ≈13.07 GB, est. 35 tok/s
- [nvidia/audio-flamingo-3-hf](https://selfhost.directory/models/nvidia/audio-flamingo-3-hf/on/rx-7800-xt): Q8_0 ≈10.05 GB, est. 39 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/tencent/weviscut/on/rtx-4060): Q4_K_M, est. 26 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/tencent/weviscut/on/apple-m4-16gb): Q6_K, est. 8.5 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/tencent/weviscut/on/rx-6700-xt): Q8_0, est. 21 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/tencent/weviscut/on/rtx-3060): Q8_0, est. 20 tok/s
- [Arc B580](https://selfhost.directory/models/tencent/weviscut/on/arc-b580): Q8_0, est. 25 tok/s
- [Tesla T4](https://selfhost.directory/models/tencent/weviscut/on/tesla-t4): Q8_0, est. 18 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/tencent/weviscut/on/arc-a770): Q8_0, est. 31 tok/s
- [Radeon RX 9070 XT](https://selfhost.directory/models/tencent/weviscut/on/rx-9070-xt): Q8_0, est. 35 tok/s

---
Model: https://selfhost.directory/models/tencent/weviscut. GPU: https://selfhost.directory/models/gpus/rx-7800-xt. Source: https://selfhost.directory/models/tencent/weviscut/on/rx-7800-xt