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 Tesla T4 run WeMM-Video-9B?

WeMM-Video-9B·10.5B·Tesla T4·16 GB VRAM

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

Yes. The Tesla T4 runs WeMM-Video-9B fully in VRAM at Q8_0 (about 12 GB of 16 GB), at roughly 16 tokens/s.

best quant
Q8_0
needs
12 GB
usable
16 GB
est. speed
~16 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 Tesla T4

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.9 GBfits~51 tok/s
Q3_K_M Noticeable loss6.5 GBfits~34 tok/s
Q4_K_M Small loss7.7 GBfits~28 tok/s
Q5_K_M Near-lossless8.8 GBfits~24 tok/s
Q6_K Near-lossless9.9 GBfits~20 tok/s
Q8_0 pickLossless12 GBfits~16 tok/s
FP16 / BF16 Lossless22 GBoffload~3.8 tok/s

Speed is a bandwidth-based estimate for generating text (320 GB/s); prompt processing and long contexts are slower.

Measured speed on the Tesla T4

No community reports for this pair yet.

Report your own speed →

Vision models that fit the Tesla T4 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
9.7BQ8_0≈11 GBFits in memory~17 tok/sCommercial OK
8.8BQ8_0≈10 GBFits in memory~19 tok/sCommercial OK
12.2BQ6_K≈13 GBFits in memory~18 tok/sConditions
10.7BQ8_0≈12 GBFits in memory~16 tok/sConditions
9.4BQ8_0≈11 GBFits in memory~18 tok/sCommercial OK
8.3BQ8_0≈8.9 GBFits in memory~20 tok/sCommercial OK

Other GPUs that run WeMM-Video-9B

Frequently asked questions

Can the Tesla T4 run WeMM-Video-9B?
Yes. The Tesla T4 runs WeMM-Video-9B fully in VRAM at Q8_0 (about 12 GB of 16 GB), at roughly 16 tokens/s.
How fast does WeMM-Video-9B run on the Tesla T4?
An estimate from memory bandwidth gives about 16 tokens/s at Q8_0.
Which quantisation of WeMM-Video-9B should I use on the Tesla T4?
Q8_0: 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.