RentGPU RentGPU
Trouver un GPU →
AI models

Every way
to use the major models.

Closed models like Claude and GPT — link to the cheapest API provider. Open-weights like Llama, Kimi, DeepSeek — choose hosted inference or self-host on rented GPUs.

5 tracked · 5 open weights · 0 closed APIs
Add a model
Modality All Text Multimodal Code Image Audio Video Vision Embedding
License All Open weights Closed / API
Size All ≤8B (edge) 8–30B (laptop) 30–100B (workstation) 100B+ (datacenter)

5 models match — reset filters

Open-weights models.

Run yourself on cheap GPUs, or use a hosted-inference provider.

Whisper Large v3

2B
by OpenAI · Whisper · 30 ctx

OpenAI's open-weight speech-to-text — the standard transcription model.

Whisper Base

0B
by OpenAI · Whisper · 30 ctx

74M Whisper — browser / Raspberry Pi-deployable.

Whisper Medium

1B
by OpenAI · Whisper · 30 ctx

769M Whisper variant — half the size of Large, 80% of the accuracy.

Whisper Small

0B
by OpenAI · Whisper · 30 ctx

244M Whisper — fits on edge GPUs and CPU.

Whisper Tiny

0B
by OpenAI · Whisper · 30 ctx

39M Whisper — runs in-browser via WebGPU.