// Cohere Command / Aya · Vision-language
command-a-plus-05-2026-bf16: VRAM & local deployment
218B total · 25B active (MoE) parameters. About 147 GB at 4-bit and 481 GB at BF16 with one 8K-token request.
released 2026-05-11licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Cohere · CohereLabs |
|---|---|
| Family / series | Cohere Command / Aya · command-a-plus |
| Type | Vision-language (image-text-to-text) |
| Parameters | 218B total · 25B active (MoE) Source: official model card“25B active parameters, 218B total parameters” |
| Context length | 195K tokens (200,000)max_position_embeddings in config.json |
| Architecture | 32 layers (8 full-attention) · 24 sliding-window layers (4096) · GQA · MoE |
| Released weights | BF16 · 438 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-05-11 (Hugging Face repo created) |
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 | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 436 GB | 481 GB | 482 GB | 485 GB | 8 × H100 (640GB) | — |
| FP8 / INT8 / Q8_0 | 232 GB | 256 GB | 257 GB | 260 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 132 GB | 147 GB | 147 GB | 151 GB | 4 × RTX PRO 6000 (384GB) | Mac 256GB |
KV cache per request: 8K 0.7 GB · 32K 1.5 GB · 128K 4.7 GB
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.
- vLLM — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
3 official repo(s) from CohereLabs.
05Other Cohere Command / Aya models
All 14 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| 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 |
| 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 |
| aya-vision-8b | 8.63B | 6.3 GB | 2025-03-02 |
06Sources
Data checked 2026-06-15. Parameters, context and licence are copied from the official repository; memory figures are our estimates.