Updated minutes ago
Canary 1B
NVIDIA · dense · 1B parameters · 4,096 context
Quality50.0
Architecture Details
TypeDENSE
Total Parameters1B
Active Parameters1B
Layers24
Hidden Dimension1,024
Attention Heads8
KV Heads8
Head Dimension128
Vocab Size128,000
Memory Requirements
BF16 Weights
2.0 GB
FP8 Weights
1.0 GB
INT4 Weights
0.5 GB
KV-Cache per Token12288 bytes
Activation Estimate0.20 GB
Fits on (single-node)
B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM BF16H100 PCIe BF16H100 NVL BF16
GPU Recommendations
RTX 3080optimal
BF16 · 1 GPU · vllm
90/100
score
Throughput
2.1K tok/s
Cost/Month
$133
Cost/M Tokens
$0.02
RTX 4060optimal
BF16 · 1 GPU · vllm
90/100
score
Throughput
734.4 tok/s
Cost/Month
$209
Cost/M Tokens
$0.11
RTX 3070optimal
BF16 · 1 GPU · vllm
90/100
score
Throughput
1.2K tok/s
Cost/Month
$85
Cost/M Tokens
$0.03
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia-nim | $0.04 | $0.04 | Cheapest |
Capabilities
Features
✗ Tool Use✗ Vision✗ Code✗ Math✗ Reasoning✓ Multilingual✗ Structured Output
Supported Frameworks
tensorrt-llmvllm
Supported Precisions
BF16 (default)FP8INT4