# Can the Arc A770 16GB run GLiDE-27B?

> Yes, but only at Q3_K_M (about 15 GB of 16 GB), which costs noticeable quality, at roughly 24 tokens/s.

Arc A770 16GB: 16 GB (16 GB usable), 560 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 10.89 | fits | 36 |
| Q3_K_M (pick) | Noticeable loss | 14.97 | fits | 24 |
| Q4_K_M | Small loss | 18.68 | offload | 8.9 |
| Q5_K_M | Near-lossless | 20.64 | offload | 5.8 |
| Q6_K | Near-lossless | 23.51 | offload | 3.9 |
| Q8_0 | Lossless | 29.6 | offload | 2.3 |
| F16 | Lossless | 53.52 | no | — |

## Run it

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

```bash
llama-server -hf kingjones777/GLiDE-27B-ROCmFP4-STRIX-GGUF:Q3_K_M
```

Docker with Vulkan (llama.cpp):

```bash
docker run -d --name llama --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-vulkan \
  -hf kingjones777/GLiDE-27B-ROCmFP4-STRIX-GGUF:Q3_K_M --host 0.0.0.0 --port 8080 -ngl 99
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="fastino/GLiDE-27B", dtype="auto", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])
```


## Vision models that fit comfortably

- [google/gemma-3-12b-it](https://selfhost.directory/models/google/gemma-3-12b-it/on/arc-a770): Q6_K ≈12.76 GB, est. 31 tok/s
- [GrootTeam/Groot-19B-A3B-261023](https://selfhost.directory/models/grootteam/groot-19b-a3b-261023/on/arc-a770): Q4_K_M ≈13.34 GB, est. 169 tok/s
- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b/on/arc-a770): Q8_0 ≈10.81 GB, est. 30 tok/s
- [google/translategemma-12b-it](https://selfhost.directory/models/google/translategemma-12b-it/on/arc-a770): Q6_K ≈12.95 GB, est. 28 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/arc-a770): Q8_0 ≈10.15 GB, est. 33 tok/s
- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-11b-vision-instruct/on/arc-a770): Q8_0 ≈11.91 GB, est. 27 tok/s

## Other GPUs that run it

- [Tesla T4](https://selfhost.directory/models/fastino/glide-27b/on/tesla-t4): Q3_K_M, est. 14 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/fastino/glide-27b/on/rx-7800-xt): Q3_K_M, est. 27 tok/s
- [Tesla P40](https://selfhost.directory/models/fastino/glide-27b/on/tesla-p40): Q5_K_M, est. 10 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/fastino/glide-27b/on/rx-7900-xtx): Q5_K_M, est. 28 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/fastino/glide-27b/on/instinct-mi50): Q8_0, est. 20 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/fastino/glide-27b/on/rtx-5090): Q8_0, est. 36 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/fastino/glide-27b/on/apple-m4-pro-48gb): Q8_0, est. 5.4 tok/s
- [RTX A6000](https://selfhost.directory/models/fastino/glide-27b/on/rtx-a6000): Q8_0, est. 15 tok/s

---
Model: https://selfhost.directory/models/fastino/glide-27b. GPU: https://selfhost.directory/models/gpus/arc-a770. Source: https://selfhost.directory/models/fastino/glide-27b/on/arc-a770