Updated minutes ago
RWKV-6 14B
RWKV Foundation · hybrid · 14.1B parameters · 32,768 context
Quality50.0
Architecture Details
TypeHYBRID
Total Parameters14.1B
Active Parameters14.1B
Layers61
Hidden Dimension5,120
Attention Heads1
KV Heads1
Head Dimension5120
Vocab Size65,536
Memory Requirements
BF16 Weights
28.2 GB
FP8 Weights
14.1 GB
INT4 Weights
7.0 GB
KV-Cache per Token0 bytes
Activation Estimate1.00 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
A100 40GB SXMoptimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
268.0 tok/s
Cost/Month
$807
Cost/M Tokens
$1.15
RTX A6000optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
132.3 tok/s
Cost/Month
$465
Cost/M Tokens
$1.34
A40optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
119.9 tok/s
Cost/Month
$399
Cost/M Tokens
$1.26
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| rwkv | $0.20 | $0.20 | Cheapest |
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✗ Math✗ Reasoning✓ Multilingual✗ Structured Output
Supported Frameworks
vllm
Supported Precisions
BF16 (default)FP8INT4