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 P40 run WeMM-Video-35BA3B?

WeMM-Video-35BA3B·36.2B (5B active)·Tesla P40·24 GB VRAM

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

Yes. The Tesla P40 runs WeMM-Video-35BA3B fully in VRAM at Q4_K_M (about 23 GB of 24 GB), at roughly 63 tokens/s.

best quant
Q4_K_M
needs
23 GB
usable
24 GB
est. speed
~63 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the WeMM-Video-35BA3B page →

Every quantisation of WeMM-Video-35BA3B on the Tesla P40

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~117 tok/s
Q3_K_M Noticeable loss18 GBfits~79 tok/s
Q4_K_M pickSmall loss23 GBfits~63 tok/s
Q5_K_M Near-lossless26 GBoffload~38 tok/s
Q6_K Near-lossless30 GBoffload~23 tok/s
Q8_0 Lossless39 GBoffload~13 tok/s
FP16 / BF16 Lossless72 GBtoo big—

Speed is a bandwidth-based estimate for generating text (347 GB/s); prompt processing and long contexts are slower.

Measured speed on the Tesla P40

No community reports for this pair yet.

Report your own speed →

Vision models that fit the Tesla P40 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
36BA3BQ4_K_M≈22 GBFits in memory~105 tok/sCommercial OK
36BA3BQ4_K_M≈23 GBFits in memory~105 tok/sCommercial OK
27.8BQ5_K_M≈22 GBFits in memory~9.7 tok/sCommercial OK
35.2BA3BQ4_K_M≈22 GBFits in memory~105 tok/sCommercial OK
meta-models logoMuse-Glimmer-30Bmeta-models
29.8BQ5_K_M≈22 GBFits in memory~9 tok/sCommercial OK
27.8BQ5_K_M≈22 GBFits in memory~9.7 tok/sCommercial OK

Other GPUs that run WeMM-Video-35BA3B

Frequently asked questions

Can the Tesla P40 run WeMM-Video-35BA3B?
Yes. The Tesla P40 runs WeMM-Video-35BA3B fully in VRAM at Q4_K_M (about 23 GB of 24 GB), at roughly 63 tokens/s.
How fast does WeMM-Video-35BA3B run on the Tesla P40?
An estimate from memory bandwidth gives about 63 tokens/s at Q4_K_M.
Which quantisation of WeMM-Video-35BA3B should I use on the Tesla P40?
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.