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 5090 run Apriel-Voice-27B-preview?

Apriel-Voice-27B-preview·27.2B·GeForce RTX 5090·32 GB VRAM

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

Yes. The RTX 5090 runs Apriel-Voice-27B-preview fully in VRAM at Q6_K (about 24 GB of 32 GB), at roughly 44 tokens/s.

best quant
Q6_K
needs
24 GB
usable
32 GB
est. speed
~44 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 5090

QuantQualityMemoryFitSpeed
Q2_K Heavy loss11 GBfits~110 tok/s
Q3_K_M Noticeable loss15 GBfits~74 tok/s
Q4_K_M Small loss19 GBfits~60 tok/s
Q5_K_M Near-lossless21 GBfits~51 tok/s
Q6_K pickNear-lossless24 GBfits~44 tok/s
Q8_0 Lossless31 GBtight~34 tok/s
FP16 / BF16 Lossless56 GBoffload~1.4 tok/s

Speed is a bandwidth-based estimate for generating text (1792 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 5090

No community reports for this pair yet.

Report your own speed →

Omni models that fit the RTX 5090 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
35.3BA3BQ6_K≈30 GBFits in memory~399 tok/sCommercial OK
24.3BQ8_0≈26 GBFits in memory~38 tok/sCommercial OK
31.7BA3BQ6_K≈27 GBFits in memory~399 tok/sCommercial OK
33BA3BQ6_K≈28 GBFits in memory~399 tok/sCommercial OK
31.7BA3BQ6_K≈27 GBFits in memory~399 tok/sCommercial OK
17.5BQ8_0≈20 GBFits in memory~53 tok/sCommercial OK

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

Frequently asked questions

Can the RTX 5090 run Apriel-Voice-27B-preview?
Yes. The RTX 5090 runs Apriel-Voice-27B-preview fully in VRAM at Q6_K (about 24 GB of 32 GB), at roughly 44 tokens/s.
How fast does Apriel-Voice-27B-preview run on the RTX 5090?
An estimate from memory bandwidth gives about 44 tokens/s at Q6_K.
Which quantisation of Apriel-Voice-27B-preview should I use on the RTX 5090?
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.