Updated minutes ago
Phi 3 Medium 14B
Microsoft · dense · 14B parameters · 131,072 context
Quality76.0
Architecture Details
TypeDENSE
Total Parameters14B
Active Parameters14B
Layers40
Hidden Dimension5,120
Attention Heads40
KV Heads10
Head Dimension128
Vocab Size32,064
Memory Requirements
BF16 Weights
28.0 GB
FP8 Weights
14.0 GB
INT4 Weights
7.0 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
299.9 tok/s
Cost/Month
$807
Cost/M Tokens
$1.02
RTX A6000optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
148.1 tok/s
Cost/Month
$465
Cost/M Tokens
$1.19
A40optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
134.2 tok/s
Cost/Month
$399
Cost/M Tokens
$1.13
API Pricing Comparison
No API pricing data available for this model.
Quality Benchmarks
MMLU78.0
HumanEval55.0
GSM8K86.0
MT-Bench82.0
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✗ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llmollama
Supported Precisions
BF16 (default)FP8INT4