NewJoin us for our inaugural conference, Forge 2026
DocsLog inGet started
Cognitive Computations logo

Dolphin 2.6 Mixtral 8x7b

Ready
model path:accounts/fireworks/models/dolphin-2p6-mixtral-8x7b
Deploy on demand

Dolphin 2.6 Mixtral 8x7b is a fine-tuned version of the Mixtral-8x7b Large Language Model specializing in coding.

Dolphin 2.6 Mixtral 8x7b API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Dolphin 2.6 Mixtral 8x7b on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
29 FEB, 2024
Kind
Base model
Provider
Cognitive Computations
Huggingface
cognitivecomputations/dolphin-2.6-mixtral-8x7b

Specifications

Calibrated
No
Mixture-of-Experts
Yes
Parameters
46B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
32.7k tokens
Function Calling
Not Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported