Autor: Jakub Rusinowski · Ostatnia aktualizacja: 4 kwietnia 2024
Zoptymalizowany specjalnie pod kątem RAG (Retrieval Augmented Generation) i użycia narzędzi. Modele Command R wyróżniają się cytowaniem źródeł i rozumowaniem nad dostarczonymi dokumentami.
| Licence | What it permits | Applies to |
|---|---|---|
CC-BY-NC-4.0 | Research / non-commercial only Research / non-commercial only — this licence does NOT permit shipping a commercial product. | Command R (35B), Command R+ (104B) |
| Command R (35B) | Min 22 GB VRAM · Q4_K_M · 128,000 ctx · ollama run command-r |
| Command R+ (104B) | Min 64 GB VRAM · Q4_K_M · 128,000 ctx · ollama run command-r-plus |
The cheapest GPU that runs Command R Family locally (min 22 GB VRAM) is the AMD Radeon RX 7900 XTX (24 GB).
Install Ollama then run: ollama run command-r
Minimum VRAM: 22 GB. For best results use Q4_K_M quantization.
Command R Family needs about 22 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Command R (35B) (22 GB, Q4_K_M); Command R+ (104B) (64 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Command R Family runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Command R Family in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run command-r. This downloads Command R Family and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.