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 Instinct MI50 32GB run h2o-lightning-31b?

h2o-lightning-31b·31.3B·Instinct MI50 32GB·32 GB VRAM

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

Yes. The Instinct MI50 32GB runs h2o-lightning-31b fully in VRAM at Q6_K (about 28 GB of 32 GB), at roughly 22 tokens/s.

best quant
Q6_K
needs
28 GB
usable
32 GB
est. speed
~22 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 Instinct MI50 32GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~55 tok/s
Q3_K_M Noticeable loss17 GBfits~37 tok/s
Q4_K_M Small loss21 GBfits~30 tok/s
Q5_K_M Near-lossless24 GBfits~25 tok/s
Q6_K pickNear-lossless28 GBfits~22 tok/s
Q8_0 Lossless35 GBoffload~7.1 tok/s
FP16 / BF16 Lossless64 GBtoo big—

Speed is a bandwidth-based estimate for generating text (1024 GB/s); prompt processing and long contexts are slower.

Measured speed on the Instinct MI50 32GB

No community reports for this pair yet.

Report your own speed →

Run h2o-lightning-31b on the Instinct MI50 32GB

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 Instinct MI50 32GB comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
31.3BQ5_K_M≈29 GBFits in memory~25 tok/sCommercial OK
27.8BQ6_K≈25 GBFits in memory~25 tok/sCommercial OK
36BA3BQ6_K≈30 GBFits in memory~228 tok/sCommercial OK
meta-models logoMuse-Glimmer-30Bmeta-models
29.8BQ8_0≈30 GBFits in memory~18 tok/sCommercial OK
27.8BQ6_K≈25 GBFits in memory~25 tok/sCommercial OK
25.8BA4BQ8_0≈29 GBFits in memory~133 tok/sCommercial OK

Other GPUs that run h2o-lightning-31b

Frequently asked questions

Can the Instinct MI50 32GB run h2o-lightning-31b?
Yes. The Instinct MI50 32GB runs h2o-lightning-31b fully in VRAM at Q6_K (about 28 GB of 32 GB), at roughly 22 tokens/s.
How fast does h2o-lightning-31b run on the Instinct MI50 32GB?
An estimate from memory bandwidth gives about 22 tokens/s at Q6_K.
Which quantisation of h2o-lightning-31b should I use on the Instinct MI50 32GB?
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.