NV EmbedQA E5 v5
NVIDIA · dense · 0.33B parameters · 512 context
Parameters
0.33B
Context Window
1K tokens
Architecture
Dense
Best GPU
B200 SXM
Cheapest API
$0.01/M
Intelligence Brief
NV EmbedQA E5 v5 is a 0.33B parameter DENSE model from NVIDIA, featuring Multi-Head Attention (MHA) with 24 layers and 1,024 hidden dimensions. With a 512 token context window, it supports multilingual. The most cost-effective API deployment is via nvidia-nim at $0.01/M output tokens. For self-hosted inference, B200 SXM delivers optimal throughput at $4261/month.
Architecture Details
Memory Requirements
BF16 Weights
0.7 GB
FP8 Weights
0.3 GB
INT4 Weights
0.2 GB
GPU Compatibility Matrix
NV EmbedQA E5 v5 is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
FP8 · 1 GPU · tensorrt-llm
83/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$4261
Cost/M Tokens
$0.46
FP8 · 1 GPU · tensorrt-llm
83/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$4271
Cost/M Tokens
$0.46
FP8 · 1 GPU · tensorrt-llm
83/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$6169
Cost/M Tokens
$0.67
Deployment Options
API Deployment
nvidia-nim
$0.01/M
output tokens
Single GPU
B200 SXM
$4261/mo
Min VRAM: 0 GB
Multi-GPU
B200 SXM
3.5K tok/s
Best available config
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia-nim | $0.01 | $0.01 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| nvidia-nimBest Value | $0.01 | $0.01 | $0 |
Cost per 1,000 Requests
Short (500 tok)
$0.00
via nvidia-nim
Medium (2K tok)
$0.02
via nvidia-nim
Long (8K tok)
$0.06
via nvidia-nim
Performance Estimates
Throughput by GPU
VRAM Breakdown (B200 SXM, FP8)
Precision Impact
bf16
0.7 GB
weights/GPU
fp8
0.3 GB
weights/GPU
~3.5K tok/s
int4
0.2 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy NV EmbedQA E5 v5
Self-Hosted Infrastructure
Similar Models
NV Retriever v1
0.33B params · dense
Quality: 50
from $0.01/M
BGE Large EN v1.5
0.335B params · dense
Quality: 50
from $0.01/M
SmolLM 360M
0.36B params · dense
Quality: 50
Whisper Small
0.244B params · dense
Quality: 50
H2O Danube3 500M
0.5B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does NV EmbedQA E5 v5 need for inference?
NV EmbedQA E5 v5 requires approximately 0.7 GB of VRAM at BF16 precision, 0.3 GB at FP8, or 0.2 GB at INT4 quantization. Additional VRAM is needed for KV-cache (12288 bytes per token) and activations (~0.10 GB).
What is the best GPU for NV EmbedQA E5 v5?
The top recommended GPU for NV EmbedQA E5 v5 is the B200 SXM using FP8 precision. It achieves approximately 3.5K tokens/sec at an estimated cost of $4261/month ($0.46/M tokens). Score: 83/100.
How much does NV EmbedQA E5 v5 inference cost?
NV EmbedQA E5 v5 API inference starts from $0.01/M input tokens and $0.01/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.