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 Arc Pro B60 run Apriel-Voice-27B-preview?

Apriel-Voice-27B-preview·27.2B·Arc Pro B60·24 GB VRAM

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

Yes. The Arc Pro B60 runs Apriel-Voice-27B-preview fully in VRAM at Q5_K_M (about 21 GB of 24 GB), at roughly 13 tokens/s.

best quant
Q5_K_M
needs
21 GB
usable
24 GB
est. speed
~13 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 Arc Pro B60

QuantQualityMemoryFitSpeed
Q2_K Heavy loss11 GBfits~28 tok/s
Q3_K_M Noticeable loss15 GBfits~19 tok/s
Q4_K_M Small loss19 GBfits~15 tok/s
Q5_K_M pickNear-lossless21 GBfits~13 tok/s
Q6_K Near-lossless24 GBoffload~10 tok/s
Q8_0 Lossless31 GBoffload~3.6 tok/s
FP16 / BF16 Lossless56 GBtoo big—

Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc Pro B60

No community reports for this pair yet.

Report your own speed →

Omni models that fit the Arc Pro B60 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
35.3BA3BQ4_K_M≈19 GBFits in memory~138 tok/sCommercial OK
24.3BQ6_K≈21 GBFits in memory~13 tok/sCommercial OK
31.7BA3BQ4_K_M≈19 GBFits in memory~138 tok/sCommercial OK
33BA3BQ4_K_M≈20 GBFits in memory~138 tok/sCommercial OK
31.7BA3BQ4_K_M≈19 GBFits in memory~138 tok/sCommercial OK
17.5BQ8_0≈20 GBFits in memory~13 tok/sCommercial OK

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

Frequently asked questions

Can the Arc Pro B60 run Apriel-Voice-27B-preview?
Yes. The Arc Pro B60 runs Apriel-Voice-27B-preview fully in VRAM at Q5_K_M (about 21 GB of 24 GB), at roughly 13 tokens/s.
How fast does Apriel-Voice-27B-preview run on the Arc Pro B60?
An estimate from memory bandwidth gives about 13 tokens/s at Q5_K_M.
Which quantisation of Apriel-Voice-27B-preview should I use on the Arc Pro B60?
Q5_K_M: 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.