Model
Model explorer

Command R7B

OPEN
Cohere · Command R family · released Dec 13, 2024

Smallest, fastest model in the R series for edge/on-device RAG and tool use; ranked first among similarly-sized open-weights models on the Open LLM Leaderboard.

ReasoningCodingVisionFunction callingTool useAgentic
519.3
Elo · rank #299
Parameters
7B
Active params
7B (dense)
Context
128K tokens
Architecture
Dense transformer (7B), optimized for on-device/edge RAG and tool use
License
CC-BY-NC-4.0 (+ Acceptable Use Policy)
Languages
23+
API price (in/out)
$0.0375 / $0.15
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
BIG-Bench HardReasoning54.9%#86
best: ERNIE 4.5 300B-A47B · 94.3%
BFCLAgents52.2%#27
best: SmolLM3 3B (No Thinking) · 92.3%
BIRD-SQLCoding42.2%#7
best: Command A · 59.5%
GPQA DiamondReasoning26.3%#274
best: GPT-5.6 · 94.6%
IFEvalReasoning77.9%#97
best: Gemma 4 26B A4B · 98.5%
MATH-500Math59.1%#115
best: GPT-5 · 99.4%
MBPP+Coding72.0%#12
best: Llama 3.1 405B · 88.6%
MMLU-ProKnowledge35.7%#158
best: Claude Fable 5 · 91.5%
MMLUKnowledge65.2%#177
best: OpenAI o3 · 92.9%
Run it locally
VRAM @ Q4
5 GB
VRAM @ FP16
14 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF Q4
Command R family
Elo progression across releases
Command RMar 2024462.5Command R7BDec 2024519.3
Resources
HFCohereLabs/c4ai-command-r7b-12-2024DOCSdocs.cohere.comAPIAvailable via Cohere API
API price $0.0375/$0.15 · each benchmark row carries its own source badge (see methodology)