Mac mini M4 64GBGünstige Wahl
64 GB Unified (+28)
C
Raises estimated decode speed by about 53%.8.7 tok/s Dekodierung
Raises estimated decode speed by about 53%.
Adds memory headroom for longer context windows and future model growth.
ca. $1,099 MSRP
Can Aya Expanse 32B run on MacBook Pro M3 Pro 36GB?
YES — With Offload
C51Usable
Estimated from fit model
Aya Expanse 32B needs ~26.7 GB VRAM. MacBook Pro M3 Pro 36GB has 25.9 GB. With Q4_K_M quantization, expect ~6 tok/s.
Runtime: llama.cppCapacity: OffloadBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth
Operating mode
Choose the run profile you care about
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
Q4_K_M (Medium quality) — 26.7 GB, 5.7 tok/s, Runs with offload (needs ~0.6 GB host RAM)
26.7 GB required25.9 GB available
103% VRAM needed
0.8 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.6 GB host RAM)
Decode
5.7 tok/s
TTFT
33837 ms
Safe context
8K
Memory
26.7 GB / 25.9 GB
Memory breakdown
Weights19.5 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom3.9 GB
See how fast it feels
See how fast it feelsAya Expanse 32B on MacBook Pro M3 Pro 36GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 5.7 tok/s decode · 33.8s TTFT (warm) · 14 tok/s prefill
What limits this setup
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
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.
Best improvement path
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs with offload | 6.1 tok/s | 17310 ms | 8K |
| Coding | C | Runs with offload (needs ~0.6 GB host RAM) | 5.7 tok/s | 33837 ms | 8K |
| Agentic Coding | C | Very compromised (needs ~2.2 GB host RAM) | 5.0 tok/s | 55857 ms | 8K |
| Reasoning | C | Runs with offload (needs ~0.6 GB host RAM) | 5.7 tok/s | 39989 ms | 8K |
| RAG | C | Very compromised (needs ~2.2 GB host RAM) | 5.0 tok/s | 69821 ms | 8K |
Quantization options
How Aya Expanse 32B (32B params) fits at each quantization level on MacBook Pro M3 Pro 36GB (25.9 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 12.5 GB | Low | B55 |
Q3_K_S | 3 | 15.7 GB | Low | B55 |
NVFP4 | 4 | 17.9 GB | Medium | C55 |
Q4_K_MBest for your GPU | 4 | 19.5 GB | Medium | C55 |
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 |
Get started
Copy-paste commands to run Aya Expanse 32B on your machine.
Run
ollama run aya-expanse:32bUpgrade-Optionen
Hardware, die Aya Expanse 32B gut ausführt
MacBook Pro M4 Pro 64GBBestes Preis-Leistungs-Verhältnis
64 GB Unified (+28)273 GB/s (+123)
B
Raises estimated decode speed by about 270%.21.1 tok/s Dekodierung
Raises estimated decode speed by about 270%.
Adds memory headroom for longer context windows and future model growth.
ca. $1,599 MSRP
MacBook Pro M4 Max 48GBApple-Upgrade
48 GB Unified (+12)546 GB/s (+396)
B
Raises estimated decode speed by about 488%.33.5 tok/s Dekodierung
Raises estimated decode speed by about 488%.
Adds memory headroom for longer context windows and future model growth.
ca. $2,499 MSRP
Frequently asked questions
Can MacBook Pro M3 Pro 36GB run Aya Expanse 32B?
Yes, MacBook Pro M3 Pro 36GB can run Aya Expanse 32B with a C grade (Runs with offload (needs ~0.6 GB host RAM)). Expected decode speed: 5.7 tok/s.
How much VRAM does Aya Expanse 32B need?
Aya Expanse 32B (32B parameters) requires approximately 26.7 GB of memory with Q4_K_M quantization.
What is the best quantization for Aya Expanse 32B?
The recommended quantization for Aya Expanse 32B is Q4_K_M, which balances quality and memory efficiency.
What speed will Aya Expanse 32B run at on MacBook Pro M3 Pro 36GB?
On MacBook Pro M3 Pro 36GB, Aya Expanse 32B achieves approximately 5.7 tokens per second decode speed with a time-to-first-token of 33837ms using Q4_K_M quantization.
Can MacBook Pro M3 Pro 36GB run Aya Expanse 32B for coding?
For coding workloads, Aya Expanse 32B on MacBook Pro M3 Pro 36GB receives a C grade with 5.7 tok/s and 8K context.
What context window can Aya Expanse 32B use on MacBook Pro M3 Pro 36GB?
On MacBook Pro M3 Pro 36GB, 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.
What should I upgrade first if Aya Expanse 32B feels slow on MacBook Pro M3 Pro 36GB?
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Is unified memory on MacBook Pro M3 Pro 36GB as fast as VRAM for Aya Expanse 32B?
Not always. MacBook Pro M3 Pro 36GB 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.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/aya-expanse-32b-on-m3-pro-36gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: