// Cohere Command / Aya · Text LLM
aya-expanse-32b: VRAM & local deployment
32.3B parameters. About 22.0 GB at 4-bit and 71.6 GB at BF16.
released 2024-10-23licence: Non-commercialmemory figures are estimates
01Specs
| Publisher | Cohere · CohereLabs |
|---|---|
| Family / series | Cohere Command / Aya · aya-expanse |
| Type | Text LLM (text-generation) |
| Parameters | 32.3B Source: counted from official safetensors weights |
| Context length | — |
| Released weights | FP16 · 64.6 GBdownload |
| Licence | CC-BY-NC-4.0 · Non-commercialResearch / non-commercial licence: commercial use is not allowed without a separate agreement. |
| Released | 2024-10-23 (Hugging Face repo created) |
| Access | Gated: accept the licence on Hugging Face before downloading. |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Smallest GPU | Mac |
|---|---|---|---|
| BF16 / FP16 (original) | 64.6 GB | H100 80GB | Mac 128GB |
| FP8 / INT8 / Q8_0 | 34.3 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 19.6 GB | RTX 5090 32GB | Mac 64GB |
KV cache not estimated: the official config.json is gated or lacks attention parameters. Totals above are weights + overhead only.
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — mentioned in the official model card
- Ollama — in the official Ollama library · aya-expanse:32b
ollama run aya-expanse:32b04Official repositories & quantised builds
1 official repo(s) from CohereLabs.
- aya-expanse-32b main
05Other Cohere Command / Aya models
All 14 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| aya-expanse-8b · same series | 8.03B | 5.9 GB | 2024-10-23 |
| North-Micro-Vision-Instruct | 2.48B | 2.7 GB | 2026-08-10 |
| North-Mini-Code-1.0 | 30B / 3B | 21.0 GB | 2026-06-05 |
| command-a-plus-05-2026-bf16 | 218B / 25B | 147 GB | 2026-05-11 |
| tiny-aya-base | 3.35B | 2.7 GB | 2026-02-13 |
| tiny-aya-global | 3.35B | 2.7 GB | 2026-02-13 |
| command-a-reasoning-08-2025 | 111.1B | 74.6 GB | 2025-08-12 |
| command-a-vision-07-2025 | 111.9B | 75.1 GB | 2025-07-28 |
| c4ai-command-a-03-2025 | 111.1B | 74.6 GB | 2025-03-11 |
06Sources
Data checked 2026-01-09. Parameters, context and licence are copied from the official repository; memory figures are our estimates.