BGE Small EN v1.5
BAAI · dense · 0.033B parameters · 512 context
Parameters
0.033B
Context Window
1K tokens
Architecture
Dense
Best GPU
B200 SXM
Intelligence Brief
BGE Small EN v1.5 is a 0.033B parameter DENSE model from BAAI, featuring Multi-Head Attention (MHA) with 12 layers and 384 hidden dimensions. With a 512 token context window, it supports general text generation. For self-hosted inference, B200 SXM delivers optimal throughput at $4261/month.
Recent changes
Loading…
Related models
5 suggestions- BGE Base EN v1.5BGE · 0.11B—
- BGE Large EN v1.5BGE · 0.335B$0.0080/M out
- BGE M3BGE · 0.568B$0.0080/M out
Nomic Embed Text v1.5Nomic Embed · 0.137B$0.0080/M out
All MiniLM L6 v2MiniLM · 0.0227B$0.0050/M out
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
0.1 GB
FP8 Weights
0.0 GB
INT4 Weights
0.0 GB
GPU Compatibility Matrix
BGE Small EN v1.5 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
No API pricing available
Single GPU
B200 SXM
$4261/mo
Min VRAM: 0 GB
Multi-GPU
B200 SXM
3.5K tok/s
Best available config
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (B200 SXM, FP8)
Precision Impact
bf16
0.1 GB
weights/GPU
fp8
0.0 GB
weights/GPU
~3.5K tok/s
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy BGE Small EN v1.5
Self-Hosted Infrastructure
Similar Models
All MiniLM L6 v2
0.0227B params · dense
Quality: 50
from $0.01/M
Whisper Base
0.074B params · dense
Quality: 50
Kokoro TTS 82M
0.082B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does BGE Small EN v1.5 need for inference?
BGE Small EN v1.5 requires approximately 0.1 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 (~0.05 GB).
What is the best GPU for BGE Small EN v1.5?
The top recommended GPU for BGE Small EN v1.5 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 BGE Small EN v1.5 inference cost?
BGE Small EN v1.5 inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.