context.vn
Menu
Models
Small Models
Speed
S3
VN Infra
Design Arena
Servers
All plans
Auction
Cloud stock
Performance
Stock watch
Sources
models.dev
arena.ai
artificialanalysis.ai
benchlm.ai
roboflow
Models
Small Models
Servers
All plans
every provider, every price
Server auction
Hetzner, one machine per row
Cloud stock
what Hetzner can create where
Performance
repeated benchmarks, and the spread
Stock watch
email me on a restock
Speed
S3
VN Infra
Design Arena
sources
models.dev
arena.ai
artificialanalysis.ai
benchlm.ai
roboflow
Small Model Hub
3,618 efficient AI models across 9 domains ·
Charts
·
API
Search
Domain
All (3,618)
Vision (1,615)
3D (743)
Embedding (472)
Multimodal (305)
Edge/Mobile (172)
Code (125)
Speech (89)
Video (49)
NLP (48)
Task
All Tasks
Speech Recognition (67)
Speech (13)
audio generation (6)
Image Classification (2)
voice activity detection (1)
Max Size
≤10M
≤50M
≤100M
≤500M
All
Max VRAM
≤512MB
≤1GB
≤2GB
≤4GB
≤8GB
All
Score
Raw
Context (0-100)
Raw benchmark score — scale varies by task
Showing 2 models
#
Model
Domain
Task
Params ↑
GFLOPs
VRAM
Score
Speed
Arch
Source
1
DeepSpeech2
Speech
Speech
94.6M
—
227 MB
—
—
—
—
Qualcomm AI Hub
2
HuggingFace-WavLM-Base-Plus
Speech
Speech
95.1M
—
228 MB
—
—
—
—
Qualcomm AI Hub