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 RTX 4060 run WeMM-Video-9B?

WeMM-Video-9B·10.5B·GeForce RTX 4060·8 GB VRAM

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

Yes, but only at Q3_K_M (about 6.5 GB of 8.0 GB), which costs noticeable quality, at roughly 29 tokens/s.

best quant
Q3_K_M
needs
6.5 GB
usable
8.0 GB
est. speed
~29 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 RTX 4060

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.9 GBfits~43 tok/s
Q3_K_M pickNoticeable loss6.5 GBfits~29 tok/s
Q4_K_M Small loss7.7 GBtight~24 tok/s
Q5_K_M Near-lossless8.8 GBoffload~15 tok/s
Q6_K Near-lossless9.9 GBoffload~10 tok/s
Q8_0 Lossless12 GBoffload~6 tok/s
FP16 / BF16 Lossless22 GBoffload~2.2 tok/s

Speed is a bandwidth-based estimate for generating text (272 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 4060

No community reports for this pair yet.

Report your own speed →

Vision models that fit the RTX 4060 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
9.7BQ4_K_M≈7.0 GBFits in memory~26 tok/sCommercial OK
8.8BQ5_K_M≈7.3 GBFits in memory~24 tok/sCommercial OK
9.4BQ4_K_M≈7.2 GBFits in memory~26 tok/sCommercial OK
8.3BQ6_K≈7.0 GBFits in memory~22 tok/sCommercial OK
10.3BQ4_K_M≈6.8 GBFits in memory~24 tok/sCommercial OK
Cloudflare logoclef-flashCloudflare
9.4BQ4_K_M≈7.4 GBFits in memory~26 tok/sCommercial OK

Other GPUs that run WeMM-Video-9B

Frequently asked questions

Can the RTX 4060 run WeMM-Video-9B?
Yes, but only at Q3_K_M (about 6.5 GB of 8.0 GB), which costs noticeable quality, at roughly 29 tokens/s.
How fast does WeMM-Video-9B run on the RTX 4060?
An estimate from memory bandwidth gives about 29 tokens/s at Q3_K_M.
Which quantisation of WeMM-Video-9B should I use on the RTX 4060?
Q3_K_M: the largest one that fits. Expected quality: noticeable 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.