Updated minutes ago
Command A
Cohere · dense · 111B parameters · 256,000 context
Quality81.0
Architecture Details
TypeDENSE
Total Parameters111B
Active Parameters111B
Layers72
Hidden Dimension10,240
Attention Heads80
KV Heads10
Head Dimension128
Vocab Size256,000
Memory Requirements
BF16 Weights
222.0 GB
FP8 Weights
111.0 GB
INT4 Weights
55.5 GB
KV-Cache per Token184320 bytes
Activation Estimate3.50 GB
Fits on (single-node)
B200 SXM FP8B100 SXM FP8GB200 NVL72 (per GPU) FP8GB300 NVL72 (per GPU) FP8H200 SXM FP8H100 SXM INT4H100 PCIe INT4H100 NVL INT4
GPU Recommendations
H20optimal
BF16 · 4 GPUs · tensorrt-llm
90/100
score
Throughput
280.0 tok/s
Cost/Month
$3758
Cost/M Tokens
$5.11
B200 NVL (pair)optimal
BF16 · 1 GPU · tensorrt-llm
88/100
score
Throughput
280.0 tok/s
Cost/Month
$9965
Cost/M Tokens
$13.54
B200 SXMoptimal
BF16 · 2 GPUs · tensorrt-llm
83/100
score
Throughput
280.0 tok/s
Cost/Month
$8522
Cost/M Tokens
$11.58
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| cohere | $2.50 | $10.00 | Cheapest |
Quality Benchmarks
MMLU83.0
HumanEval55.0
GSM8K88.0
MT-Bench84.0
Capabilities
Features
✓ Tool Use✗ Vision✓ Code✓ Math✓ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
Supported Precisions
BF16 (default)