Can I Run Aya Expanse on NVIDIA L40S?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
Yes, comfortably — Aya Expanse 32B at Q4_K_M needs 21.6 GB at 8K context (19.5 GB weights + 2.1 GB KV cache/overhead), leaving ~26.4 GB of the NVIDIA L40S's 48 GB, at ~36 tok/s (est.), with room for up to 64K context.
See what else this hardware can run →
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
NVIDIA L40S Specs
| VRAM | 48 GB |
| Memory Bandwidth | 864 GB/s |
Aya Expanse 32B on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 66.7 GB | ✗ No | — | — |
| Q8_0 | 36.5 GB | ✓ Yes | 64K | Build for this |
| Q6_K | 28.6 GB | ✓ Yes | 64K | — |
| Q5_K_M | 25 GB | ✓ Yes | 64K | Build for this |
| Q4_K_M | 21.6 GB | ✓ Yes | 64K | Build for this |
| Q3_K_M | 15.9 GB | ✓ Yes | 64K | — |
| Q2_K | 12.8 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 48 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA L40S: 8K 21.6 GB · 32K 25.7 GB · 125K 41.3 GB. Every window this model publishes still fits 48 GB.
No compatible GPU? Aya Expanse 32B on 32 GB of system RAM, CPU only: runs comfortably.
Aya Expanse Sizes That Fit the NVIDIA L40S (at 8K context)
| Aya Expanse 32B | Q4_K_M · 21.6 GB at 8K context · ~36 tok/s (est.) |
| Aya Expanse 8B | Q4_K_M · 6.7 GB at 8K context · ~111 tok/s (est.) |
At 2 hrs/day, buying (~$7,499) beats renting at $0.34/hr after about 30.6 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Aya Expanse on the NVIDIA L40S — does it fit?
Yes, comfortably — Aya Expanse 32B at Q4_K_M needs 21.6 GB at 8K context (19.5 GB weights + 2.1 GB KV cache/overhead), leaving ~26.4 GB of the NVIDIA L40S's 48 GB, at ~36 tok/s (est.), with room for up to 64K context.
Which Aya Expanse variant fits best on the NVIDIA L40S?
Aya Expanse 32B at Q4_K_M quantization needs 21.6 GB at 8K context (19.5 GB weights + 2.1 GB KV cache/overhead), estimated ~36 tokens/sec, up to 64K context.
Every Aya Expanse size on the NVIDIA L40S
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| Aya Expanse 32B | 21.6 GB | Runs | ~36 tok/s |
| Aya Expanse 8B | 6.7 GB | Runs | ~111 tok/s |
Aya Expanse on Other GPUs
- Aya Expanse on NVIDIA RTX 6000 Ada Generation
- Aya Expanse on Apple M3 Pro
- Aya Expanse on NVIDIA GeForce RTX 5090
- Aya Expanse on Apple M4
- Aya Expanse on Apple M2 Pro
Popular Models on the NVIDIA L40S
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Aya Expanse Model Page | NVIDIA L40S GPU Page | VRAM calculator | Check Your Hardware