Skip to content
Updated minutes ago
Mistral

NV EmbedQA Mistral 7B

NVIDIA · dense · 7.24B parameters · 32,768 context

Quality
50.0

Parameters

7.24B

Context Window

32K tokens

Architecture

Dense

Best GPU

A10G

Cheapest API

$0.01/M

Intelligence Brief

NV EmbedQA Mistral 7B is a 7.24B parameter DENSE model from NVIDIA, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 32,768 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, A10G delivers optimal throughput at $285/month.

Architecture Details

TypeDENSE
Total Parameters7.24B
Active Parameters7.24B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size32,000

Memory Requirements

BF16 Weights

14.5 GB

FP8 Weights

7.2 GB

INT4 Weights

3.6 GB

KV-Cache per Token65536 bytes
Activation Estimate0.70 GB

GPU Compatibility Matrix

NV EmbedQA Mistral 7B is compatible with 95% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
B300288GB
B100 SXM192GB
GB200 NVL72 (per GPU)192GB
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
H200 SXM141GB
H2096GB
GH20096GB
Ada Lovelace(11 GPUs)
L40S48GB
L4048GB
RTX 6000 Ada48GB
L2048GB
Ampere(16 GPUs)
A100 80GB SXM80GB
A100 80GB PCIe80GB
A1664GB
RTX A600048GB
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

A10Goptimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

223.7 tok/s

Latency (ITL)

4.5ms

Est. TTFT

1ms

Cost/Month

$285

Cost/M Tokens

$0.48

Use this config →
A30optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

347.9 tok/s

Latency (ITL)

2.9ms

Est. TTFT

0ms

Cost/Month

$332

Cost/M Tokens

$0.36

Use this config →
RTX 4090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

375.9 tok/s

Latency (ITL)

2.7ms

Est. TTFT

0ms

Cost/Month

$370

Cost/M Tokens

$0.37

Use this config →

Deployment Options

API

API Deployment

nvidia-nim

$0.01/M

output tokens

Self-Hosted

Single GPU

A10G

$285/mo

Min VRAM: 7 GB

Scale

Multi-GPU

RTX 3080 x2

439.3 tok/s

TP· $266/mo

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
nvidia-nim$0.01$0.01
Cheapest

Cost Analysis

ProviderInput $/MOutput $/M~Monthly Cost
nvidia-nimBest Value$0.01$0.01$0

Cost per 1,000 Requests

Short (500 tok)

$0.01

via nvidia-nim

Medium (2K tok)

$0.03

via nvidia-nim

Long (8K tok)

$0.12

via nvidia-nim

Performance Estimates

Throughput by GPU

A10G
223.7 tok/s
A30
347.9 tok/s
RTX 4090
375.9 tok/s

VRAM Breakdown (A10G, BF16)

Weights
Act
Weights 14.5 GBKV-Cache 2.1 GBActivations 5.6 GBOverhead 1.2 GB

Precision Impact

bf16

14.5 GB

weights/GPU

~223.7 tok/s

fp8

7.2 GB

weights/GPU

int4

3.6 GB

weights/GPU

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

tensorrt-llmvllmsglang

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy NV EmbedQA Mistral 7B

Similar Models

Smaller context, More expensiveCompare →

Frequently Asked Questions

How much VRAM does NV EmbedQA Mistral 7B need for inference?

NV EmbedQA Mistral 7B requires approximately 14.5 GB of VRAM at BF16 precision, 7.2 GB at FP8, or 3.6 GB at INT4 quantization. Additional VRAM is needed for KV-cache (65536 bytes per token) and activations (~0.70 GB).

What is the best GPU for NV EmbedQA Mistral 7B?

The top recommended GPU for NV EmbedQA Mistral 7B is the A10G using BF16 precision. It achieves approximately 223.7 tokens/sec at an estimated cost of $285/month ($0.48/M tokens). Score: 100/100.

How much does NV EmbedQA Mistral 7B inference cost?

NV EmbedQA Mistral 7B 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.