All MiniLM L6 v2
Sentence Transformers · dense · 0.0227B parameters · 256 context
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
Memory Requirements
BF16 Weights
0.0 GB
FP8 Weights
0.0 GB
INT4 Weights
0.0 GB
GPU Compatibility Matrix
All MiniLM L6 v2 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
huggingface
$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 |
|---|---|---|---|
| huggingface | $0.01 | $0.01 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/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
VRAM Breakdown (B200 SXM, FP8)
Precision Impact
bf16
0.0 GB
weights/GPU
fp8
0.0 GB
weights/GPU
~3.5K tok/s
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy All MiniLM L6 v2
Self-Hosted Infrastructure
Similar Models
BGE Small EN v1.5
0.033B params · dense
Quality: 50
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.