Skip to content
Updated minutes ago
SentenceTransformers

All MiniLM L6 v2

Sentence Transformers · dense · 0.0227B parameters · 256 context

Quality
50.0

Parameters

0.0227B

Context Window

0K tokens

Architecture

Dense

Best GPU

B200 SXM

Cheapest API

$0.01/M

Intelligence Brief

All MiniLM L6 v2 is a 0.0227B parameter DENSE model from Sentence Transformers, featuring Multi-Head Attention (MHA) with 6 layers and 384 hidden dimensions. With a 256 token context window, it supports general text generation. The most cost-effective API deployment is via huggingface at $0.01/M output tokens. For self-hosted inference, B200 SXM delivers optimal throughput at $4261/month.

Architecture Details

TypeDENSE
Total Parameters0.0227B
Active Parameters0.0227B
Layers6
Hidden Dimension384
Attention Heads12
KV Heads12
Head Dimension32
Vocab Size30,522

Memory Requirements

BF16 Weights

0.0 GB

FP8 Weights

0.0 GB

INT4 Weights

0.0 GB

KV-Cache per Token9216 bytes
Activation Estimate0.01 GB

GPU Compatibility Matrix

All MiniLM L6 v2 is compatible with 100% 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
GH20096GB
Ada Lovelace(11 GPUs)
L40S48GB
RTX 6000 Ada48GB
Ampere(16 GPUs)
A100 80GB SXM80GB
A100 80GB PCIe80GB
RTX A600048GB
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

B200 SXMoptimal

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

Use this config →
B100 SXMoptimal

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

Use this config →
GB200 NVL72 (per GPU)optimal

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

Use this config →

Deployment Options

API

API Deployment

huggingface

$0.01/M

output tokens

Self-Hosted

Single GPU

B200 SXM

$4261/mo

Min VRAM: 0 GB

Scale

Multi-GPU

B200 SXM

3.5K tok/s

Best available config

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
huggingface$0.01$0.01
Cheapest

Cost Analysis

ProviderInput $/MOutput $/M~Monthly Cost
huggingfaceBest Value$0.01$0.01$0

Cost per 1,000 Requests

Short (500 tok)

$0.00

via huggingface

Medium (2K tok)

$0.01

via huggingface

Long (8K tok)

$0.05

via huggingface

Performance Estimates

Throughput by GPU

B200 SXM
3.5K tok/s
B100 SXM
3.5K tok/s
GB200 NVL72 (per GPU)
3.5K tok/s

VRAM Breakdown (B200 SXM, FP8)

KV
Act
Weights 0.0 GBKV-Cache 0.1 GBActivations 0.1 GBOverhead 0.0 GB

Precision Impact

bf16

0.0 GB

weights/GPU

fp8

0.0 GB

weights/GPU

~3.5K tok/s

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

tgiollama

Supported Precisions

BF16 (default)FP8

Where to Deploy All MiniLM L6 v2

Similar Models

Frequently Asked Questions

How much VRAM does All MiniLM L6 v2 need for inference?

All MiniLM L6 v2 requires approximately 0.0 GB of VRAM at BF16 precision, 0.0 GB at FP8, or 0.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (9216 bytes per token) and activations (~0.01 GB).

What is the best GPU for All MiniLM L6 v2?

The top recommended GPU for All MiniLM L6 v2 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 All MiniLM L6 v2 inference cost?

All MiniLM L6 v2 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.