Aya Expanse 32B needs ~28.0 GB VRAM. NVIDIA A40 48GB has 48.0 GB. With Q4_K_M quantization, expect ~28 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
30.2 tok/s
TTFT
6401 ms
Safe context
8K
Memory
28.0 GB / 48.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 30.2 tok/s | 3491 ms | 8K |
| Coding | B | Runs well | 27.8 tok/s | 6961 ms | 8K |
| Agentic Coding | B | Runs well | 30.2 tok/s | 9311 ms | 8K |
| Reasoning | B | Runs well | 30.2 tok/s | 7565 ms | 8K |
| RAG | B | Runs well | 30.2 tok/s | 11638 ms | 8K |
How Aya Expanse 32B (32B params) fits at each quantization level on NVIDIA A40 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 12.5 GB | Low | C49 |
Q3_K_S | 3 | 15.7 GB | Low | C50 |
NVFP4 | 4 |
Copy-paste commands to run Aya Expanse 32B on your machine.
Run
ollama run aya-expanse:32bYes, NVIDIA A40 48GB can run Aya Expanse 32B with a B grade (Runs well). Expected decode speed: 27.8 tok/s.
Aya Expanse 32B (32B parameters) requires approximately 28.0 GB of memory with Q4_K_M quantization.
The recommended quantization for Aya Expanse 32B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA A40 48GB, Aya Expanse 32B achieves approximately 27.8 tokens per second decode speed with a time-to-first-token of 6961ms using Q4_K_M quantization.
For coding workloads, Aya Expanse 32B on NVIDIA A40 48GB receives a B grade with 27.8 tok/s and 8K context.
On NVIDIA A40 48GB, Aya Expanse 32B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/aya-expanse-32b-on-a40-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
17.9 GB |
| Medium |
| C51 |
Q4_K_M | 4 | 19.5 GB | Medium | C51 |
Q5_K_M | 5 | 23.0 GB | High | C53 |
Q6_K | 6 | 26.2 GB | High | C54 |
Q8_0Best for your GPU | 8 | 34.2 GB | Very High | C53 |
F16 | 16 | 65.6 GB | Maximum | F0 |