Updated minutes ago
Phi 3 Mini 3.8B
Microsoft · dense · 3.8B parameters · 131,072 context
Quality64.0
Architecture Details
TypeDENSE
Total Parameters3.8B
Active Parameters3.8B
Layers32
Hidden Dimension3,072
Attention Heads32
KV Heads32
Head Dimension96
Vocab Size32,064
Memory Requirements
BF16 Weights
7.6 GB
FP8 Weights
3.8 GB
INT4 Weights
1.9 GB
KV-Cache per Token393216 bytes
Activation Estimate0.50 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
A4000optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
286.5 tok/s
Cost/Month
$161
Cost/M Tokens
$0.21
RTX 4080optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
458.5 tok/s
Cost/Month
$304
Cost/M Tokens
$0.25
RTX 4070 Tioptimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
322.3 tok/s
Cost/Month
$237
Cost/M Tokens
$0.28
API Pricing Comparison
No API pricing data available for this model.
Quality Benchmarks
MMLU68.8
HumanEval47.0
GSM8K75.0
MT-Bench76.0
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✗ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llmollama
Supported Precisions
BF16 (default)FP8INT4