Can the Tesla T4 run Apriel-Voice-27B-preview?
Apriel-Voice-27B-preview·27.2B·Tesla T4·16 GB VRAM
Just about. At Q3_K_M it needs about 15 GB of the 16 GB available, so keep the context short, at roughly 13 tokens/s.
- best quant
- Q3_K_M
- needs
- 15 GB
- usable
- 16 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 Tesla T4
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 11 GB | fits | ~20 tok/s |
| Q3_K_M pick | 15 GB | tight | ~13 tok/s |
| Q4_K_M | 19 GB | offload | ~6.7 tok/s |
| Q5_K_M | 21 GB | offload | ~4.4 tok/s |
| Q6_K | 24 GB | offload | ~3.2 tok/s |
| Q8_0 | 31 GB | offload | ~2 tok/s |
| FP16 / BF16 | 56 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (320 GB/s); prompt processing and long contexts are slower.
Measured speed on the Tesla T4
No community reports for this pair yet.
Report your own speed →Omni models that fit the Tesla T4 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 17.5B | Q6_K | ≈9.3 GBFits in memory | ~12 tok/s | |
| 12B | Q6_K | ≈13 GBFits in memory | ~18 tok/s | |
| 14.7B | Q6_K | ≈13 GBFits in memory | ~15 tok/s | |
| 10.7B | Q8_0 | ≈8.9 GBFits in memory | ~15 tok/s | |
| 17.1B | Q5_K_M | ≈15 GBFits in memory | ~14 tok/s | |
| 12B | Q6_K | ≈13 GBFits in memory | ~18 tok/s |
Other GPUs that run Apriel-Voice-27B-preview
Frequently asked questions
- Can the Tesla T4 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 13 tokens/s.
- How fast does Apriel-Voice-27B-preview run on the Tesla T4?
- An estimate from memory bandwidth gives about 13 tokens/s at Q3_K_M.
- Which quantisation of Apriel-Voice-27B-preview should I use on the Tesla T4?
- 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.