Aya Expanse 32B needs ~18.4 GB VRAM. MacBook Pro M3 24GB has 17.3 GB. With Q2_K quantization, expect ~5 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
8.2 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
2.3 tok/s
TTFT
85603 ms
Safe context
4K
Memory
25.5 GB / 17.3 GB
Offload
30%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 0.8 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 2.2 tok/s | 47987 ms | 4K |
| Coding | F | Too heavy | 2.1 tok/s | 93093 ms | 4K |
| Agentic Coding | F | Too heavy | 2.0 tok/s | 140800 ms | 4K |
| Reasoning | F | Too heavy | 2.1 tok/s | 110019 ms | 4K |
| RAG | F | Too heavy | 2.0 tok/s | 176000 ms | 4K |
How Aya Expanse 32B (32B params) fits at each quantization level on MacBook Pro M3 24GB (17.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 12.5 GB | Low | B56 |
Q3_K_S | 3 | 15.7 GB | Low | F0 |
NVFP4 | 4 | 17.9 GB | Medium | F0 |
Q4_K_M | 4 | 19.5 GB | Medium | F0 |
Q5_K_M | 5 | 23.0 GB | High | F0 |
Q6_K | 6 | 26.2 GB | High | F0 |
Q8_0 | 8 | 34.2 GB | Very High | F0 |
F16 | 16 | 65.6 GB | Maximum | F0 |
Copy-paste commands to run Aya Expanse 32B on your machine.
Run
ollama run aya-expanse:32bOpciones de mejora
Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Sube la velocidad estimada de decodificación alrededor de un 204%.
~$799 MSRP
Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.
~$1,099 MSRP
Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Sube la velocidad estimada de decodificación alrededor de un 204%.
~$1,099 MSRP
NVIDIA A100 40GBMayor saltoHace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.
~$10,000 MSRP
Yes, MacBook Pro M3 24GB can run Aya Expanse 32B at Q2_K quantization (Runs with offload (needs ~0.8 GB host RAM)). The recommended Q4_K_M requires 25.5 GB which exceeds available memory, but at Q2_K it needs only 18.4 GB. Expected decode speed: 4.5 tok/s.
Aya Expanse 32B (32B parameters) requires approximately 25.5 GB at Q4_K_M quantization. On MacBook Pro M3 24GB, it fits at Q2_K using 18.4 GB.
The recommended quantization is Q4_K_M, but on MacBook Pro M3 24GB the best fitting quantization is Q2_K, which uses 18.4 GB.
On MacBook Pro M3 24GB, Aya Expanse 32B achieves approximately 4.5 tokens per second decode speed with a time-to-first-token of 43068ms using Q2_K quantization.
For coding workloads, Aya Expanse 32B on MacBook Pro M3 24GB receives a F grade with 2.1 tok/s and 4K context.
On MacBook Pro M3 24GB, Aya Expanse 32B can safely use up to 8K tokens of context at Q2_K quantization. The model's official context limit is 8K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Not always. MacBook Pro M3 24GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/aya-expanse-32b-on-m3-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: