Can the Radeon RX 7800 XT run GroundAnything-VLM?
GroundAnything-VLM·4.8B·Radeon RX 7800 XT·16 GB VRAM
Yes. The Radeon RX 7800 XT runs GroundAnything-VLM fully in VRAM at FP16 / BF16 (about 11 GB of 16 GB), at roughly 35 tokens/s.
- best quant
- FP16 / BF16
- needs
- 11 GB
- usable
- 16 GB
- est. speed
- ~35 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the GroundAnything-VLM page →
Every quantisation of GroundAnything-VLM on the Radeon RX 7800 XT
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.2 GB | fits | ~216 tok/s |
| Q3_K_M | 3.9 GB | fits | ~145 tok/s |
| Q4_K_M | 4.3 GB | fits | ~117 tok/s |
| Q5_K_M | 5.0 GB | fits | ~100 tok/s |
| Q6_K | 5.5 GB | fits | ~86 tok/s |
| Q8_0 | 6.7 GB | fits | ~67 tok/s |
| FP16 / BF16 pick | 11 GB | fits | ~35 tok/s |
Speed is a bandwidth-based estimate for generating text (624 GB/s); prompt processing and long contexts are slower.
Measured speed on the Radeon RX 7800 XT
No community reports for this pair yet.
Report your own speed →Run GroundAnything-VLM on the Radeon RX 7800 XT
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="GroundingPI/GroundAnything-VLM", 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 the Radeon RX 7800 XT comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4.7B | Q8_0 | ≈5.9 GBFits in memory | ~69 tok/s | |
| 4.3B | Q8_0 | ≈5.2 GBFits in memory | ~75 tok/s | |
| 4.4B | Q8_0 | ≈5.8 GBFits in memory | ~73 tok/s | |
| 5B | Q8_0 | ≈5.6 GBFits in memory | ~65 tok/s | |
| 4.3B | Q8_0 | ≈5.6 GBFits in memory | ~75 tok/s | |
| 3.8B | Q8_0 | ≈4.0 GBFits in memory | ~86 tok/s |
Other GPUs that run GroundAnything-VLM
Frequently asked questions
- Can the Radeon RX 7800 XT run GroundAnything-VLM?
- Yes. The Radeon RX 7800 XT runs GroundAnything-VLM fully in VRAM at FP16 / BF16 (about 11 GB of 16 GB), at roughly 35 tokens/s.
- How fast does GroundAnything-VLM run on the Radeon RX 7800 XT?
- An estimate from memory bandwidth gives about 35 tokens/s at FP16 / BF16.
- Which quantisation of GroundAnything-VLM should I use on the Radeon RX 7800 XT?
- FP16 / BF16: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.