Updated minutes ago
Phi-4
Microsoft · dense · 14.7B parameters · 16,384 context
Quality83.0
Architecture Details
TypeDENSE
Total Parameters14.7B
Active Parameters14.7B
Layers40
Hidden Dimension5,120
Attention Heads40
KV Heads10
Head Dimension128
Vocab Size100,352
Memory Requirements
BF16 Weights
29.4 GB
FP8 Weights
14.7 GB
INT4 Weights
7.3 GB
KV-Cache per Token204800 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
A100 40GB SXMoptimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
285.6 tok/s
Cost/Month
$807
Cost/M Tokens
$1.07
RTX A6000optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
141.1 tok/s
Cost/Month
$465
Cost/M Tokens
$1.25
A40optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
127.8 tok/s
Cost/Month
$399
Cost/M Tokens
$1.19
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| azure | $0.07 | $0.14 | Cheapest |
| together | $0.20 | $0.20 |
Quality Benchmarks
MMLU84.8
HumanEval67.0
GSM8K93.0
MT-Bench85.0
Capabilities
Features
✓ Tool Use✗ Vision✓ Code✓ Math✓ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llmollama
Supported Precisions
BF16 (default)FP8INT4