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.

h2oai logo

Can the Arc Pro B60 run h2o-lightning-31b?

h2o-lightning-31b·31.3B·Arc Pro B60·24 GB VRAM

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

Yes. The Arc Pro B60 runs h2o-lightning-31b fully in VRAM at Q4_K_M (about 21 GB of 24 GB), at roughly 13 tokens/s.

best quant
Q4_K_M
needs
21 GB
usable
24 GB
est. speed
~13 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the h2o-lightning-31b page →

Every quantisation of h2o-lightning-31b on the Arc Pro B60

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~24 tok/s
Q3_K_M Noticeable loss17 GBfits~16 tok/s
Q4_K_M pickSmall loss21 GBfits~13 tok/s
Q5_K_M Near-lossless24 GBoffload~11 tok/s
Q6_K Near-lossless28 GBoffload~5.2 tok/s
Q8_0 Lossless35 GBoffload~2.5 tok/s
FP16 / BF16 Lossless64 GBtoo big—

Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc Pro B60

No community reports for this pair yet.

Report your own speed →

Run h2o-lightning-31b on the Arc Pro B60

Transformers · Ask about an imagedocs
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="h2oai/h2o-lightning-31b", 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"])

Gated on Hugging Face: accept the licence on the model page and export HF_TOKEN first.

Vision models that fit the Arc Pro B60 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
27.8BQ5_K_M≈22 GBFits in memory~13 tok/sCommercial OK
36BA3BQ4_K_M≈22 GBFits in memory~138 tok/sCommercial OK
meta-models logoMuse-Glimmer-30Bmeta-models
29.8BQ5_K_M≈22 GBFits in memory~12 tok/sCommercial OK
27.8BQ5_K_M≈22 GBFits in memory~13 tok/sCommercial OK
25.8BA4BQ5_K_M≈20 GBFits in memory~88 tok/sCommercial OK
36BA3BQ4_K_M≈23 GBFits in memory~138 tok/sCommercial OK

Other GPUs that run h2o-lightning-31b

Frequently asked questions

Can the Arc Pro B60 run h2o-lightning-31b?
Yes. The Arc Pro B60 runs h2o-lightning-31b fully in VRAM at Q4_K_M (about 21 GB of 24 GB), at roughly 13 tokens/s.
How fast does h2o-lightning-31b run on the Arc Pro B60?
An estimate from memory bandwidth gives about 13 tokens/s at Q4_K_M.
Which quantisation of h2o-lightning-31b should I use on the Arc Pro B60?
Q4_K_M: the largest one that fits. Expected quality: small loss 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.