Updated minutes ago
Whisper Large V3
OpenAI · dense · 1.55B parameters · 448 context
Quality50.0
Architecture Details
TypeDENSE
Total Parameters1.55B
Active Parameters1.55B
Layers32
Hidden Dimension1,280
Attention Heads20
KV Heads20
Head Dimension64
Vocab Size51,866
Memory Requirements
BF16 Weights
3.1 GB
FP8 Weights
1.6 GB
INT4 Weights
0.8 GB
KV-Cache per Token163840 bytes
Activation Estimate0.30 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
A4000optimal
BF16 · 1 GPU · vllm
90/100
score
Throughput
741.3 tok/s
Cost/Month
$161
Cost/M Tokens
$0.08
RTX 4080optimal
BF16 · 1 GPU · vllm
90/100
score
Throughput
1.2K tok/s
Cost/Month
$304
Cost/M Tokens
$0.10
RTX 4070 Tioptimal
BF16 · 1 GPU · vllm
90/100
score
Throughput
834.0 tok/s
Cost/Month
$237
Cost/M Tokens
$0.11
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| openai | $0.01 | $0.01 | Cheapest |
Capabilities
Features
✗ Tool Use✗ Vision✗ Code✗ Math✗ Reasoning✓ Multilingual✗ Structured Output
Supported Frameworks
vllmtensorrt-llm
Supported Precisions
BF16 (default)FP8INT4