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.

tencent logo

Can the Arc B570 run WeMM-Video-9B?

WeMM-Video-9B·10.5B·Arc B570·10 GB VRAM

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

Yes. The Arc B570 runs WeMM-Video-9B fully in VRAM at Q5_K_M (about 8.8 GB of 10 GB), at roughly 28 tokens/s.

best quant
Q5_K_M
needs
8.8 GB
usable
10 GB
est. speed
~28 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the WeMM-Video-9B page →

Every quantisation of WeMM-Video-9B on the Arc B570

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.9 GBfits~61 tok/s
Q3_K_M Noticeable loss6.5 GBfits~41 tok/s
Q4_K_M Small loss7.7 GBfits~33 tok/s
Q5_K_M pickNear-lossless8.8 GBfits~28 tok/s
Q6_K Near-lossless9.9 GBtight~24 tok/s
Q8_0 Lossless12 GBoffload~9.2 tok/s
FP16 / BF16 Lossless22 GBoffload~2.5 tok/s

Speed is a bandwidth-based estimate for generating text (380 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc B570

No community reports for this pair yet.

Report your own speed →

Vision models that fit the Arc B570 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
9.7BQ6_K≈8.8 GBFits in memory~26 tok/sCommercial OK
8.8BQ6_K≈8.2 GBFits in memory~29 tok/sCommercial OK
10.7BQ5_K_M≈9.2 GBFits in memory~28 tok/sConditions
9.4BQ6_K≈9.1 GBFits in memory~27 tok/sCommercial OK
8.3BQ8_0≈8.9 GBFits in memory~24 tok/sCommercial OK
10.3BQ6_K≈8.9 GBFits in memory~25 tok/sCommercial OK

Other GPUs that run WeMM-Video-9B

Frequently asked questions

Can the Arc B570 run WeMM-Video-9B?
Yes. The Arc B570 runs WeMM-Video-9B fully in VRAM at Q5_K_M (about 8.8 GB of 10 GB), at roughly 28 tokens/s.
How fast does WeMM-Video-9B run on the Arc B570?
An estimate from memory bandwidth gives about 28 tokens/s at Q5_K_M.
Which quantisation of WeMM-Video-9B should I use on the Arc B570?
Q5_K_M: 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.