Command R 35B
by Cohere · command-r family
35B
parameters
text-generation reasoning multilingual tool-use summarization
Command R 35B is Cohere's open-weight model optimized for retrieval-augmented generation (RAG), tool use, and enterprise workflows. It supports 128K context and 10 languages, with particular strength in grounded generation that cites sources accurately. This model stands out for its native tool-use capabilities and reliable instruction following. It is well-suited for building AI applications that need to interact with external APIs, databases, and search systems while maintaining factual accuracy.
Quick Start with Ollama
ollama run 35b-v0.1-q4_K_M | Creator | Cohere |
| Parameters | 35B |
| Architecture | transformer-decoder |
| Context Length | 128K tokens |
| License | CC-BY-NC-4.0 |
| Released | Mar 11, 2024 |
| Ollama | command-r |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M recommended | 17.4 GB | 22.5 GB |
★
★
★
★
★
| 35b-v0.1-q4_K_M |
| Q5_K_M | 20.3 GB | 26 GB |
★
★
★
★
★
| 35b-v0.1-q5_K_M |
| Q8_0 | 31.5 GB | 37 GB |
★
★
★
★
★
| 35b-v0.1-q8_0 |
Compatible Hardware for Q4_K_M
Showing compatibility for the recommended quantization (Q4_K_M, 22.5 GB VRAM).
Compatible Hardware
9 hardware
device(s) cannot run this model configuration.
Benchmark Scores
75.0
mmlu