Skip to content

Command A 111B

by Cohere · command-r family

111B

parameters

text-generation code-generation reasoning multilingual tool-use math summarization

Command A 111B is Cohere's next-generation enterprise model, succeeding Command R+ with improved reasoning, math, and agentic capabilities. It features a 256K context window and strong multilingual support, designed for complex tool-use workflows and document-heavy applications. The model delivers significant improvements over its predecessor across coding, mathematical reasoning, and multi-step tool orchestration. It remains optimized for RAG and enterprise deployment scenarios where accuracy and source grounding are critical.

Quick Start with Ollama

ollama run q4_K_M
Resources Ollama Hugging Face Official Page
Creator Cohere
Parameters 111B
Architecture transformer-decoder
Context 256K tokens
Released Mar 13, 2025
License CC-BY-NC-4.0
Ollama command-a

Quantization Options

Format File Size VRAM Required Quality Ollama Tag
Q4_K_M rec 56 GB 61 GB q4_K_M
Q8_0 111 GB 117 GB q8_0

Compatible Hardware

Q4_K_M requires 61 GB VRAM

Compatible Hardware

HardwareVRAMTypeFitEst. Speed
Mac Studio M4 Ultra 512GB512 GBmacRuns~13 tok/s
Mac Pro M2 Ultra 192GB192 GBmacRuns~13 tok/s
Mac Studio M4 Ultra 192GB192 GBmacRuns~13 tok/s
Mac Studio M4 Max 128GB128 GBmacRuns~9 tok/s
MacBook Pro M4 Max 128GB128 GBmacRuns~9 tok/s
MacBook Pro M5 Max 128GB128 GBmacRuns~9 tok/s
NVIDIA RTX PRO 6000 Blackwell96 GBgpuRuns~31 tok/s
MacBook Pro M3 Max 96GB96 GBmacRuns~7 tok/s
Mac mini M4 Pro 64GB64 GBmacCPU Offload~1 tok/s
Mac Studio M4 Max 64GB64 GBmacCPU Offload~3 tok/s
MacBook Pro M4 Max 64GB64 GBmacCPU Offload~3 tok/s
MacBook Pro M5 Max 64GB64 GBmacCPU Offload~3 tok/s
NVIDIA RTX 6000 Ada Generation48 GBgpuCPU Offload~5 tok/s
NVIDIA RTX A600048 GBgpuCPU Offload~4 tok/s
NVIDIA RTX PRO 5000 Blackwell48 GBgpuCPU Offload~5 tok/s
Mac mini M4 Pro 48GB48 GBmacCPU Offload~1 tok/s
MacBook Pro M3 Max 48GB48 GBmacCPU Offload~2 tok/s
MacBook Pro M4 Pro 48GB48 GBmacCPU Offload~1 tok/s
MacBook Pro M4 Max 48GB48 GBmacCPU Offload~3 tok/s
MacBook Pro M5 Max 48GB48 GBmacCPU Offload~2 tok/s
MacBook Pro M5 Pro 48GB48 GBmacCPU Offload~1 tok/s
86 hardware device(s) cannot run this model at Q4_K_M.

Benchmark Scores

78.0
mmlu