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.

ServiceNow-AI logo

Can the RTX A6000 run Apriel-Voice-27B-preview?

Apriel-Voice-27B-preview·27.2B·RTX A6000·48 GB VRAM

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

Yes. The RTX A6000 runs Apriel-Voice-27B-preview fully in VRAM at Q8_0 (about 31 GB of 48 GB), at roughly 15 tokens/s.

best quant
Q8_0
needs
31 GB
usable
48 GB
est. speed
~15 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Apriel-Voice-27B-preview page →

Every quantisation of Apriel-Voice-27B-preview on the RTX A6000

QuantQualityMemoryFitSpeed
Q2_K Heavy loss11 GBfits~47 tok/s
Q3_K_M Noticeable loss15 GBfits~32 tok/s
Q4_K_M Small loss19 GBfits~26 tok/s
Q5_K_M Near-lossless21 GBfits~22 tok/s
Q6_K Near-lossless24 GBfits~19 tok/s
Q8_0 pickLossless31 GBfits~15 tok/s
FP16 / BF16 Lossless56 GBoffload~3 tok/s

Speed is a bandwidth-based estimate for generating text (768 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX A6000

No community reports for this pair yet.

Report your own speed →

Omni models that fit the RTX A6000 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
35.3BA3BQ8_0≈33 GBFits in memory~133 tok/sCommercial OK
24.3BQ8_0≈26 GBFits in memory~16 tok/sCommercial OK
31.7BA3BQ8_0≈33 GBFits in memory~133 tok/sCommercial OK
33BA3BQ8_0≈34 GBFits in memory~133 tok/sCommercial OK
31.7BA3BQ8_0≈34 GBFits in memory~133 tok/sCommercial OK
17.5BQ8_0≈20 GBFits in memory~23 tok/sCommercial OK

Other GPUs that run Apriel-Voice-27B-preview

Frequently asked questions

Can the RTX A6000 run Apriel-Voice-27B-preview?
Yes. The RTX A6000 runs Apriel-Voice-27B-preview fully in VRAM at Q8_0 (about 31 GB of 48 GB), at roughly 15 tokens/s.
How fast does Apriel-Voice-27B-preview run on the RTX A6000?
An estimate from memory bandwidth gives about 15 tokens/s at Q8_0.
Which quantisation of Apriel-Voice-27B-preview should I use on the RTX A6000?
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.