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 Radeon RX 6700 XT run WeMM-Video-9B?

WeMM-Video-9B·10.5B·Radeon RX 6700 XT·12 GB VRAM

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

Yes. The Radeon RX 6700 XT runs WeMM-Video-9B fully in VRAM at Q6_K (about 9.9 GB of 12 GB), at roughly 24 tokens/s.

best quant
Q6_K
needs
9.9 GB
usable
12 GB
est. speed
~24 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 Radeon RX 6700 XT

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 Near-lossless8.8 GBfits~28 tok/s
Q6_K pickNear-lossless9.9 GBfits~24 tok/s
Q8_0 Lossless12 GBoffload~16 tok/s
FP16 / BF16 Lossless22 GBoffload~2.9 tok/s

Speed is a bandwidth-based estimate for generating text (384 GB/s); prompt processing and long contexts are slower.

Measured speed on the Radeon RX 6700 XT

No community reports for this pair yet.

Report your own speed →

Vision models that fit the Radeon RX 6700 XT comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
9.7BQ8_0≈11 GBFits in memory~21 tok/sCommercial OK
8.8BQ8_0≈10 GBFits in memory~23 tok/sCommercial OK
12.2BQ4_K_M≈10 GBFits in memory~29 tok/sConditions
10.7BQ6_K≈10 GBFits in memory~24 tok/sConditions
9.4BQ8_0≈11 GBFits in memory~21 tok/sCommercial OK
8.3BQ8_0≈8.9 GBFits in memory~24 tok/sCommercial OK

Other GPUs that run WeMM-Video-9B

Frequently asked questions

Can the Radeon RX 6700 XT run WeMM-Video-9B?
Yes. The Radeon RX 6700 XT runs WeMM-Video-9B fully in VRAM at Q6_K (about 9.9 GB of 12 GB), at roughly 24 tokens/s.
How fast does WeMM-Video-9B run on the Radeon RX 6700 XT?
An estimate from memory bandwidth gives about 24 tokens/s at Q6_K.
Which quantisation of WeMM-Video-9B should I use on the Radeon RX 6700 XT?
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.