Cohere
Aya Expanse 32B (32B parameters) requires approximately 23.8 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 28 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Aya Expanse 32B on your machine.
Run
ollama run aya-expanse:32bQuick specs
About this model
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 12.5 GB | Low | — |
Q3_K_S | 3 | 15.7 GB | Low | — |
NVFP4 | 4 | 17.9 GB | Medium | — |
Q4_K_M | 4 | 19.5 GB | Medium | — |
Q5_K_M | 5 | 23.0 GB | High | — |
Q6_K | 6 | 26.2 GB | High | — |
Q8_0 | 8 | 34.2 GB | Very High | — |
F16 | 16 | 65.6 GB | Maximum | — |
Quality benchmarks
Reasoning
General
Source: community · 2024-10-01
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Aya Expanse 32B (32B parameters) requires approximately 23.8 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Mac mini M4 64GB can run Aya Expanse 32B with a compatibility score of 54/100. It provides 64 GB of memory and achieves approximately 8.7 tokens per second.
The recommended quantization for Aya Expanse 32B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Aya Expanse 32B: NVIDIA A100 40GB (score: 61/100), AMD Instinct MI100 32GB (score: 60/100), RTX 5090 32GB (score: 60/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Aya Expanse 32B is well-suited for chat as well as multilingual. It was designed with these use cases in mind.
See also
