The Open-Source AI Stack
RSS
All models

Models · command

Command R+

Source-available Cohere · 2024-04-04 · CC BY-NC 4.0

Cohere released Command R+ as a 104B dense model with 128K context, optimized for retrieval-augmented generation, multi-step tool use, and grounded citation. Production weights remain proprietary, but Cohere Labs published the research weights on Hugging Face under CC BY-NC 4.0, making it source-available for non-commercial use.

Architecture

tokens in Embedding vocab not disclosed · command-r tokenizer × N layers Grouped-Query Attention RoPE context 131,072 tokens Dense MLP SwiGLU activation (standard) 104B active params Output projection tokens out
Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture
dense
Total params
not disclosed
Active params
104B
Context window
not verified
Attention
gqa
Position encoding
rope
Post-training
sft, dpo
OSI-approved
no
Data released
no
Training code
not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

Recommended use cases

  • retrieval-augmented generation with citations
  • agentic tool-use workflows
  • non-commercial research under CC BY-NC

Available quantizations

GGUF llama.cpp's container; the common local format, k-quants from Q2 to Q8. runs on llama.cpp, Ollama
FP8 8-bit float, frequently a native release on Hopper / Blackwell GPUs. runs on vLLM, SGLang, TensorRT-LLM

Verified via the Hugging Face model tree ↗. Community quantizations change over time; the families shown are those with published weights at audit time.

Notable innovations

  • · Grounded generation with citation templates
  • · Multi-step tool use in the base chat template
  • · Optimized for 10 business languages

Known limitations

  • · CC BY-NC 4.0 forbids commercial use of the open weights; production use requires the Cohere API. source ↗

Lineage

Larger sibling of Command R (35B). Superseded by Command R+ 08-2024 and later Command A releases on the production API.

Sources