Updated minutes ago
GPT-3.5 Turbo
OpenAI · dense · 20B parameters · 16,384 context
Quality67.0
Architecture Details
TypeDENSE
Total Parameters20B
Active Parameters20B
Layers40
Hidden Dimension5,120
Attention Heads40
KV Heads8
Head Dimension128
Vocab Size100,000
Memory Requirements
BF16 Weights
40.0 GB
FP8 Weights
20.0 GB
INT4 Weights
10.0 GB
KV-Cache per Token40960 bytes
Activation Estimate1.50 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
H100 SXMoptimal
BF16 · 1 GPU · tensorrt-llm
100/100
score
Throughput
722.3 tok/s
Cost/Month
$1794
Cost/M Tokens
$0.94
H100 PCIeoptimal
BF16 · 1 GPU · tensorrt-llm
100/100
score
Throughput
431.2 tok/s
Cost/Month
$1794
Cost/M Tokens
$1.58
H20optimal
BF16 · 1 GPU · tensorrt-llm
95/100
score
Throughput
862.5 tok/s
Cost/Month
$940
Cost/M Tokens
$0.41
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| openai | $0.50 | $1.50 | Cheapest |
Quality Benchmarks
MMLU70.0
HumanEval48.1
GSM8K57.1
MT-Bench79.0
Capabilities
Features
✓ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
Supported Precisions
BF16 (default)