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 Radeon RX 9070 XT run Apriel-Voice-27B-preview?

Apriel-Voice-27B-preview·27.2B·Radeon RX 9070 XT·16 GB VRAM

Saved in this browser, used on every model page.
Just about

Just about. At Q3_K_M it needs about 15 GB of the 16 GB available, so keep the context short, at roughly 26 tokens/s.

best quant
Q3_K_M
needs
15 GB
usable
16 GB
est. speed
~26 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 Radeon RX 9070 XT

QuantQualityMemoryFitSpeed
Q2_K Heavy loss11 GBfits~39 tok/s
Q3_K_M pickNoticeable loss15 GBtight~26 tok/s
Q4_K_M Small loss19 GBoffload~9.2 tok/s
Q5_K_M Near-lossless21 GBoffload~5.3 tok/s
Q6_K Near-lossless24 GBoffload~3.6 tok/s
Q8_0 Lossless31 GBoffload~2.2 tok/s
FP16 / BF16 Lossless56 GBtoo big—

Speed is a bandwidth-based estimate for generating text (640 GB/s); prompt processing and long contexts are slower.

Measured speed on the Radeon RX 9070 XT

No community reports for this pair yet.

Report your own speed →

Omni models that fit the Radeon RX 9070 XT comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
17.5BQ6_K≈9.3 GBFits in memory~24 tok/sCommercial OK
12BQ6_K≈13 GBFits in memory~36 tok/sCommercial OK
ByteDance-Seed logoBAGEL-7B-MoTByteDance-Seed
14.7BQ6_K≈13 GBFits in memory~29 tok/sCommercial OK
10.7BQ8_0≈8.9 GBFits in memory~31 tok/sCommercial OK
HiDream-ai logoHiDream-E1-FullHiDream-ai
17.1BQ5_K_M≈15 GBFits in memory~29 tok/sCommercial OK
12BQ6_K≈13 GBFits in memory~36 tok/sCommercial OK

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

Frequently asked questions

Can the Radeon RX 9070 XT run Apriel-Voice-27B-preview?
Just about. At Q3_K_M it needs about 15 GB of the 16 GB available, so keep the context short, at roughly 26 tokens/s.
How fast does Apriel-Voice-27B-preview run on the Radeon RX 9070 XT?
An estimate from memory bandwidth gives about 26 tokens/s at Q3_K_M.
Which quantisation of Apriel-Voice-27B-preview should I use on the Radeon RX 9070 XT?
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.