NVIDIA H20 96GBBudget pick4000 GB/s (+3454)
C
Raises estimated decode speed by about 439%.180.5 tok/s decode
Raises estimated decode speed by about 439%.
Adds memory headroom for longer context windows and future model growth.
~$12,000 MSRP
Aya Expanse 32B needs ~33.2 GB VRAM. MacBook Pro M4 Max 96GB has 69.1 GB. With Q4_K_M quantization, expect ~34 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
33.5 tok/s
TTFT
5786 ms
Safe context
8K
Memory
33.2 GB / 69.1 GB
This setup is broadly balanced for this model.
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 33.5 tok/s | 3156 ms | 8K |
| Coding | C | Runs well | 33.5 tok/s | 5786 ms | 8K |
| Agentic Coding | B | Runs well | 33.5 tok/s | 8416 ms | 8K |
| Reasoning | C | Runs well | 33.5 tok/s | 6838 ms | 8K |
| RAG | B | Runs well | 33.5 tok/s | 10520 ms | 8K |
Inference speed
Estimated decode speed (tokens/sec) for Aya Expanse 32B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~43 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
| RTX 5090 32GB | 32 GB | Q4_K_M | 43.3 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 33.5 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 33.5 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 31.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 25.9 | Offloads |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 25.9 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 24.5 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.1 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 16.6 | Offloads |
| RTX 3090 24GB | 24 GB | Q4_K_M | 15.2 | Offloads |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 13.4 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 12.3 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 10.2 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 3.6 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.2 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Aya Expanse 32B (32B params) fits at each quantization level on MacBook Pro M4 Max 96GB (69.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 12.5 GB | Low | C47 |
Q3_K_S | 3 | 15.7 GB | Low | C47 |
NVFP4 | 4 | 17.9 GB | Medium | C48 |
Q4_K_M | 4 | 19.5 GB | Medium | C48 |
Q5_K_M | 5 | 23.0 GB | High | C49 |
Q6_K | 6 | 26.2 GB | High | C50 |
Q8_0Best for your GPU | 8 | 34.2 GB | Very High | C52 |
F16 | 16 | 65.6 GB | Maximum | F0 |
Copy-paste commands to run Aya Expanse 32B on your machine.
Run
ollama run aya-expanse:32bUpgrade options
NVIDIA H20 96GBBudget pickRaises estimated decode speed by about 439%.
Adds memory headroom for longer context windows and future model growth.
~$12,000 MSRP
NVIDIA A100 80GBBest valueRaises estimated decode speed by about 185%.
~$15,000 MSRP
Yes, MacBook Pro M4 Max 96GB can run Aya Expanse 32B with a C grade (Runs well). Expected decode speed: 33.5 tok/s.
Aya Expanse 32B (32B parameters) requires approximately 33.2 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 MacBook Pro M4 Max 96GB, Aya Expanse 32B achieves approximately 33.5 tokens per second decode speed with a time-to-first-token of 5786ms using Q4_K_M quantization.
For coding workloads, Aya Expanse 32B on MacBook Pro M4 Max 96GB receives a C grade with 33.5 tok/s and 8K context.
On MacBook Pro M4 Max 96GB, 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.
Not always. MacBook Pro M4 Max 96GB 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-m4-max-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: