// Cohere Command / Aya · Text LLM
North-Mini-Code-1.0: VRAM & local deployment
30B total · 3B active (MoE) parameters. About 21.0 GB at 4-bit and 67.0 GB at BF16 with one 8K-token request.
released 2026-06-05licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Cohere · CohereLabs |
|---|---|
| Family / series | Cohere Command / Aya · North-Mini-Code-1.0 |
| Type | Text LLM (text-generation) |
| Parameters | 30B total · 3B active (MoE) Source: official model card“Model Size: 30B total; 3B active” |
| Context length | 488K tokens (500,000)max_position_embeddings in config.json |
| Architecture | 49 layers (13 full-attention) · 36 sliding-window layers (4096) · GQA · MoE |
| Released weights | BF16 · 61.0 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-06-05 (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) | 60.0 GB | 67.0 GB | 67.7 GB | 70.3 GB | H100 80GB | Mac 128GB |
| FP8 / INT8 / Q8_0 | 31.9 GB | 36.1 GB | 36.7 GB | 39.4 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 18.2 GB | 21.0 GB | 21.7 GB | 24.3 GB | RTX 4090 24GB | Mac 36GB |
KV cache per request: 8K 0.5 GB · 32K 1.2 GB · 128K 3.8 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
- Ollama — in the official Ollama library · north-mini-code-1.0
ollama run north-mini-code-1.004Official 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 |
| 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 |
| 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.