LLM Reference

Dolphin 2.5 Mixtral 8x7B

Released
2023-12-18
Last refreshed
2026-06-15
Status
Researched 60d ago
Open sourceCommercial use: permittedCodingClassification

Dolphin 2.5 Mixtral 8x7B is a released coding and classification model with open-source; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating coding and classification
  • Workloads that can use a 32k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
Dolphin
Released
2023-12-18
Context
32k
Parameters
8x7B
Architecture
Mixture of Experts
Knowledge cutoff
2023-12
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Uncensored AI models for open access

N/A
Founded N/A
Website
Pricing

No tracked provider token pricing is available yet.

About

The Dolphin 2.5 Mixtral 8x7B is a sophisticated large language model designed primarily for coding tasks, known for its proficiency across diverse programming languages including Kotlin. It utilizes the Mixtral-8x7b architecture and has been fine-tuned on datasets like Dolphin-Coder and MagiCoder, employing qLoRA and Axolotl during training. Featuring a 16k context window for fine-tuning and a base context window of 32k, it offers powerful yet uncensored capabilities, allowing it to handle a wide range of prompts, albeit this introduces ethical considerations. The model is available in various formats on platforms like Hugging Face, catering to different needs with options such as GGUF and GPTQ quantization levels. Despite its strengths, users should be mindful of ethical sensitivities and implement alignment measures when deploying it publicly.

Dolphin 2.5 Mixtral 8x7B is an open-source model in the Dolphin family. The structured metadata tracks a 32k-token context window. This page tracks provider routes through Together AI, with the cheapest tracked route listed at $0.6 input and $0.6 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 44.8, HellaSwag 89.0, and HumanEval 67.9.

Top use-case fit: coding, agents, and build tasks

Coding

1 relevant benchmark in the decision map.

Classification

2 relevant benchmarks in the decision map.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
Google-Proof Q&A44.8diamondObserved 2026-03-06Source
HellaSwag89.010-shotObserved 2026-03-06Source
HumanEval67.9pass@1Observed 2026-03-06Source
Massive Multitask Language Understanding71.25-shotObserved 2026-03-06Source

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Dolphin 2.5 Mixtral 8x7B?

Dolphin 2.5 Mixtral 8x7B has a context window of 32k tokens.

How much does Dolphin 2.5 Mixtral 8x7B cost?

Dolphin 2.5 Mixtral 8x7B is available at $0.6/1M input tokens through Together AI.

When was Dolphin 2.5 Mixtral 8x7B released?

Dolphin 2.5 Mixtral 8x7B was released on 2023-12-18.

Which providers offer Dolphin 2.5 Mixtral 8x7B?

Dolphin 2.5 Mixtral 8x7B is available from 1 provider: Together AI.

What benchmarks has Dolphin 2.5 Mixtral 8x7B been tested on?

Dolphin 2.5 Mixtral 8x7B has been evaluated on 4 benchmarks, including Google-Proof Q&A, HellaSwag, HumanEval, Massive Multitask Language Understanding.