LLM Reference

OpenChat 2 x OpenOrca

Released
2023-12-28
Last refreshed
2026-04-15
Status
Researched 154d ago

OpenChat 2 x OpenOrca has model metadata, but missing tracked provider pricing keeps it from being a default production pick.

Use it for

  • Teams evaluating general LLM work
  • Workloads that can use a 2k 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
Released
2023-12-28
Context
2k
Parameters
13B
Architecture
Decoder Only
Specialization
general
Training
finetuned
Created by

Human-centered approach to safe AI

N/A
Founded N/A
Website
Pricing

No tracked provider token pricing is available yet.

About

OpenChat V2 x OpenOrca Preview 2 is a beta release large language model developed on the OpenChat V2 architecture for advanced text generation tasks. Built upon the comprehensive 4.5 million-item OpenOrca dataset, it includes a special end-of-turn token for effective conversation management. Despite some potential bugs or incomplete features due to its beta status, it shows promising performance in preliminary AGIEval results. The model is compatible with the OpenChat V2 vLLM OpenAI API server for easy deployment, with a parameter size of 13 billion and a memory requirement of 7.5 GB VRAM. However, its performance can vary based on different prompting and sampling parameters 12.

OpenChat 2 x OpenOrca is a model in the OpenChat 2 family. The structured metadata tracks a 2k-token context window. No headline benchmark score is tracked for OpenChat 2 x OpenOrca yet.

Top use-case fit

No primary decision-task fit is mapped for this model yet.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Rankings & picks(4)