Phi 3 Small 7B
Microsoft · dense · 7B parameters · 131,072 context
Parameters
7B
Context Window
128K tokens
Architecture
Dense
Best GPU
A10G
Quality Score
72/100
Intelligence Brief
Phi 3 Small 7B is a 7B parameter DENSE model from Microsoft, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 131,072 token context window, it supports structured output, code, math. On standardized benchmarks, it achieves MMLU 75.7, HumanEval 52, GSM8K 82. For self-hosted inference, A10G delivers optimal throughput at $285/month.
Architecture Details
Memory Requirements
BF16 Weights
14.0 GB
FP8 Weights
7.0 GB
INT4 Weights
3.5 GB
GPU Compatibility Matrix
Phi 3 Small 7B is compatible with 95% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
231.4 tok/s
Latency (ITL)
4.3ms
Est. TTFT
1ms
Cost/Month
$285
Cost/M Tokens
$0.47
BF16 · 1 GPU · vllm
100/100
score
Throughput
359.9 tok/s
Latency (ITL)
2.8ms
Est. TTFT
0ms
Cost/Month
$332
Cost/M Tokens
$0.35
BF16 · 1 GPU · vllm
100/100
score
Throughput
388.8 tok/s
Latency (ITL)
2.6ms
Est. TTFT
0ms
Cost/Month
$370
Cost/M Tokens
$0.36
Deployment Options
API Deployment
No API pricing available
Single GPU
A10G
$285/mo
Min VRAM: 7 GB
Multi-GPU
RTX 3080 x2
452.6 tok/s
TP· $266/mo
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (A10G, BF16)
Precision Impact
bf16
14.0 GB
weights/GPU
~231.4 tok/s
fp8
7.0 GB
weights/GPU
int4
3.5 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Phi 3 Small 7B
Self-Hosted Infrastructure
Similar Models
Phi 3 Mini 3.8B
3.8B params · dense
Quality: 64
Phi 3 Medium 14B
14B params · dense
Quality: 76
OLMo 2 7B
7B params · dense
Quality: 50
Command R 7B
7B params · dense
Quality: 68
from $0.15/M
Falcon 7B
7B params · dense
Quality: 37
from $0.15/M
Frequently Asked Questions
How much VRAM does Phi 3 Small 7B need for inference?
Phi 3 Small 7B requires approximately 14.0 GB of VRAM at BF16 precision, 7.0 GB at FP8, or 3.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (131072 bytes per token) and activations (~1.00 GB).
What is the best GPU for Phi 3 Small 7B?
The top recommended GPU for Phi 3 Small 7B is the A10G using BF16 precision. It achieves approximately 231.4 tokens/sec at an estimated cost of $285/month ($0.47/M tokens). Score: 100/100.
How much does Phi 3 Small 7B inference cost?
Phi 3 Small 7B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.