selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

GroundingPI logo

Can the Arc A380 run GroundAnything-VLM?

GroundAnything-VLM·4.8B·Arc A380·6 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The Arc A380 runs GroundAnything-VLM fully in VRAM at Q6_K (about 5.5 GB of 6.0 GB), at roughly 26 tokens/s.

best quant
Q6_K
needs
5.5 GB
usable
6.0 GB
est. speed
~26 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 Arc A380

QuantQualityMemoryFitSpeed
Q2_K Heavy loss3.2 GBfits~64 tok/s
Q3_K_M Noticeable loss3.9 GBfits~43 tok/s
Q4_K_M Small loss4.3 GBfits~35 tok/s
Q5_K_M Near-lossless5.0 GBfits~30 tok/s
Q6_K pickNear-lossless5.5 GBfits~26 tok/s
Q8_0 Lossless6.7 GBoffload~16 tok/s
FP16 / BF16 Lossless11 GBoffload~5.4 tok/s

Speed is a bandwidth-based estimate for generating text (186 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc A380

No community reports for this pair yet.

Report your own speed →

Run GroundAnything-VLM on the Arc A380

Transformers · Ask about an imagedocs
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 Arc A380 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
4.7BQ6_K≈4.9 GBFits in memory~27 tok/sCommercial OK
4.3BQ8_0≈5.2 GBFits in memory~22 tok/sConditions
4.4BQ6_K≈4.9 GBFits in memory~28 tok/sCommercial OK
5BQ8_0≈5.6 GBFits in memory~19 tok/sConditions
4.3BQ8_0≈5.6 GBFits in memory~22 tok/sConditions
4.3BQ8_0≈5.6 GBFits in memory~22 tok/sConditions

Other GPUs that run GroundAnything-VLM

Frequently asked questions

Can the Arc A380 run GroundAnything-VLM?
Yes. The Arc A380 runs GroundAnything-VLM fully in VRAM at Q6_K (about 5.5 GB of 6.0 GB), at roughly 26 tokens/s.
How fast does GroundAnything-VLM run on the Arc A380?
An estimate from memory bandwidth gives about 26 tokens/s at Q6_K.
Which quantisation of GroundAnything-VLM should I use on the Arc A380?
Q6_K: the largest one that fits. Expected quality: near-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.