Skip to content
Updated minutes ago
Mistral

Ministral 8B

Mistral AI · dense · 8B parameters · 131,072 context

Quality
50.0

Parameters

8B

Context Window

128K tokens

Architecture

Dense

Best GPU

A30

Cheapest API

$0.10/M

Intelligence Brief

Ministral 8B is a 8B parameter DENSE model from Mistral AI, featuring Grouped Query Attention (GQA) with 36 layers and 4,096 hidden dimensions. With a 131,072 token context window, it supports tools, structured output, code, math, multilingual. The most cost-effective API deployment is via mistral at $0.10/M output tokens. For self-hosted inference, A30 delivers optimal throughput at $332/month.

Architecture Details

TypeDENSE
Total Parameters8B
Active Parameters8B
Layers36
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size32,768

Memory Requirements

BF16 Weights

16.0 GB

FP8 Weights

8.0 GB

INT4 Weights

4.0 GB

KV-Cache per Token147456 bytes
Activation Estimate1.00 GB

GPU Compatibility Matrix

Ministral 8B is compatible with 90% 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

A30optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

314.9 tok/s

Latency (ITL)

3.2ms

Est. TTFT

1ms

Cost/Month

$332

Cost/M Tokens

$0.40

Use this config →
RTX 4090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

340.2 tok/s

Latency (ITL)

2.9ms

Est. TTFT

1ms

Cost/Month

$370

Cost/M Tokens

$0.41

Use this config →
RTX 3090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

315.9 tok/s

Latency (ITL)

3.2ms

Est. TTFT

1ms

Cost/Month

$180

Cost/M Tokens

$0.22

Use this config →

Deployment Options

API

API Deployment

mistral

$0.10/M

output tokens

Self-Hosted

Single GPU

A30

$332/mo

Min VRAM: 8 GB

Scale

Multi-GPU

RTX 3060 x2

190.4 tok/s

TP· $114/mo

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
mistral$0.10$0.10
Cheapest

Cost Analysis

ProviderInput $/MOutput $/M~Monthly Cost
mistralBest Value$0.10$0.10$1

Cost per 1,000 Requests

Short (500 tok)

$0.07

via mistral

Medium (2K tok)

$0.28

via mistral

Long (8K tok)

$1.00

via mistral

Performance Estimates

Throughput by GPU

A30
314.9 tok/s
RTX 4090
340.2 tok/s
RTX 3090
315.9 tok/s

VRAM Breakdown (A30, BF16)

Weights
Act
Weights 16.0 GBKV-Cache 2.4 GBActivations 8.0 GBOverhead 1.3 GB

Precision Impact

bf16

16.0 GB

weights/GPU

~314.9 tok/s

fp8

8.0 GB

weights/GPU

int4

4.0 GB

weights/GPU

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llmollama

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Ministral 8B

Similar Models

Aya 23 8B

8B params · dense

Quality: 50

from $0.60/M

Smaller context, More expensiveCompare →
Higher quality, More expensiveCompare →

Llama 3 8B

8B params · dense

Quality: 63

from $0.20/M

Smaller context, Higher quality, More expensiveCompare →

Llama Guard 3 8B

8B params · dense

Quality: 50

from $0.20/M

More expensiveCompare →

Minitron 8B

8B params · dense

Quality: 62

from $0.10/M

Smaller context, Higher qualityCompare →

Frequently Asked Questions

How much VRAM does Ministral 8B need for inference?

Ministral 8B requires approximately 16.0 GB of VRAM at BF16 precision, 8.0 GB at FP8, or 4.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (147456 bytes per token) and activations (~1.00 GB).

What is the best GPU for Ministral 8B?

The top recommended GPU for Ministral 8B is the A30 using BF16 precision. It achieves approximately 314.9 tokens/sec at an estimated cost of $332/month ($0.40/M tokens). Score: 100/100.

How much does Ministral 8B inference cost?

Ministral 8B API inference starts from $0.10/M input tokens and $0.10/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.