← Back to Artificial Intelligence
Official logo has not been verified.
Artificial Intelligence / Multiple Model Sites
Dolphin Chat
Dolphin Chat is linked by the Dolphin publisher from its model card. The publisher also releases downloadable Dolphin models, which are separate from the hosted chat service.
tool · Limited available evidence · Checked 2026-10-04
Overview
Dolphin Chat is linked by the Dolphin publisher from its model card. The publisher also releases downloadable Dolphin models, which are separate from the hosted chat service.[1]
Use cases
- Explore the downloadable Dolphin Mistral 24B Venice Edition for self-hosted conversational applications with a configurable system prompt.[1]
Features
- The related model card documents Transformers, vLLM, SGLang and local-app workflows. Its deployment example uses image inputs and a 131,072-token setting.[1]
Limitations
- The unquantized GPU example requires over 60 GB of GPU memory. This model card does not prove the hosted chat uses the same configuration.[1]
Specifications
Verified 2026-10-04. Versions and access terms can change.
| Related downloadable model | Dolphin-Mistral-24B-Venice-Edition; 24B parameters, BF16; Apache-2.0[1] |
|---|
Public user feedback
Attributed external experiences. These are separate from verified specifications and vendor claims.
No attributable user reviews have been verified for this entry yet.
Links
Sources and evidence gaps
- Dolphin publisher model card and official chat linkrepository · checked 2026-10-04
- The chat endpoint returned HTTP 403. Current hosted models, no-sign-up access, unlimited use and prices could not be confirmed.
- No hosted-chat mark was confidently matched.
- No identifiable independent user review was verified for this entry. Vendor claims are not a user rating.