Command R+ 104B
Cohere's flagship — RAG-tuned, multilingual. Open weights but non-commercial.
Our verdict
Positioning
Command R+ is Cohere's enterprise-aimed open-weight flagship — 104B parameters with explicit training for retrieval-augmented generation and tool-call workflows. The model to pick when RAG is the primary workload and you can afford workstation-class hardware.
Strengths
- Best-in-class RAG behavior — explicitly trained on citation-aware retrieval.
- Strong multilingual — better than Llama on European + Asian languages.
- Mature tool-use format — Cohere's API conventions translate cleanly.
Limitations
- CC-BY-NC license for non-commercial only — commercial deployment requires a separate Cohere license.
- 104B VRAM cost — ~58 GB at Q4, partial-offload required on 24 GB cards.
- General-chat quality below Llama 3.3 70B despite the size advantage.
Performance evidence
The earlier timing ranges were not tied to a published run. Use the benchmark records for measured results and compare their full configurations.
Should you run this locally?
Yes, for RAG-heavy non-commercial work, or commercial deployments with the Cohere license. No, for general-purpose chat — Llama 3.3 70B is more memory-efficient and equally good.
How it compares
- vs Llama 3.3 70B → Llama wins on general use + license; Command R+ wins on RAG specifically.
- vs Command R 35B → 104B is meaningfully smarter; 35B is the practical-VRAM Cohere pick.
- vs DeepSeek R1 Distill Llama 70B → R1 Distill wins on reasoning; Command R+ wins on RAG/tool-use behavior.
Run this yourself
ollama pull command-r-plus:104b-q4_K_M
ollama run command-r-plus:104b-q4_K_M
›Why this rating
7.8/10 — Cohere's enterprise-tuned 104B with built-in RAG and tool-use scaffolding. Excellent at structured RAG workflows, but eclipsed by Llama 3.3 70B for general use. Loses points on license restrictiveness and VRAM cost.
Overview
Cohere's flagship — RAG-tuned, multilingual. Open weights but non-commercial.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- Best open RAG model at release
- Multilingual
Weaknesses
- Non-commercial
- 70GB+ VRAM
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 60.0 GB | 70 GB |
At Q4 Command R+ 104B needs about 70 GB of memory by our estimate, more than a 32 GB graphics card holds. Renting a GPU with enough memory (or several GPUs) by the hour is the practical way to try it before you plan hardware for it.
Referral links: RunLocalAI may earn a commission or account credits if you sign up and rent, at no extra cost to you. Hourly rates and which GPUs are listed change all the time, so check the provider's page before you start. How we make money.
Get the model
Ollama
One-line install
ollama run command-r-plus:104bRead our Ollama review →HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Command R+ 104B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Command R+ 104B?
Can I use Command R+ 104B commercially?
What's the context length of Command R+ 104B?
How do I install Command R+ 104B with Ollama?
Source: huggingface.co/CohereForAI/c4ai-command-r-plus
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Command R+ 104B runs on your specific hardware before committing money.