Skip to content
Updated minutes ago
Microsoft

Phi-4

Microsoft · dense · 14.7B parameters · 16,384 context

Quality
83.0

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

Use this config →
RTX A6000optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

141.1 tok/s

Cost/Month

$465

Cost/M Tokens

$1.25

Use this config →
A40optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

127.8 tok/s

Cost/Month

$399

Cost/M Tokens

$1.19

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
azure$0.07$0.14
Cheapest
together$0.20$0.20

Quality Benchmarks

MMLU
84.8
HumanEval
67.0
GSM8K
93.0
MT-Bench
85.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llmollama

Supported Precisions

BF16 (default)FP8INT4

Similar Models