Ling 3.0 TinyAnt Group
|
Solar MiniUpstage AI
|
|||||
Related Products
|
||||||
About
Ling 3.0 Tiny is an open-weights reasoning model with 7.9B total parameters, 1.3B active parameters, and a 262K-token context window. Built with a mixture-of-experts architecture, it extends the open-weights Pareto frontier for intelligence versus active parameters and is small enough to run locally in many settings. The model scores 25 on the Artificial Analysis Intelligence Index, comparable to gpt-oss-120b (high, 24) while using 15x fewer total parameters and 4x fewer active parameters. This parameter efficiency comes with relatively high token usage, with 213M output tokens required to run the Intelligence Index. Ling 3.0 Tiny also shows substantial improvements in hallucination behavior over Ling-mini-2.0, improving its AA-Omniscience score by 59 points while maintaining similar accuracy. Rather than guessing when uncertain, it attempted only 37% of questions in the evaluation, resulting in a 30% hallucination rate compared with 96% for the previous generation.
|
About
Solar Mini is a preβtrained large language model that delivers GPTβ3.5βcomparable responses with 2.5Γ faster inference while staying under 30β―billion parameters. It achieved first place on the Hugging Face Open LLM Leaderboard in Decemberβ―2023 by combining a 32βlayer Llamaβ―2 architecture, initialized with highβquality Mistralβ―7B weights, with an innovative βdepth upβscalingβ (DUS) approach that deepens the model efficiently without adding complex modules. After DUS, continued pretraining restores and enhances performance, and instruction tuning in a QA format, especially for Korean, refines its ability to follow user prompts, while alignment tuning ensures its outputs meet human or advanced AI preferences. Solar Mini outperforms competitors such as Llamaβ―2, Mistralβ―7B, KoβAlpaca, and KULLM across a variety of benchmarks, proving that compact size need not sacrifice capability.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
AI developers, researchers, and teams seeking to run, evaluate, customize, or integrate a compact open-weights reasoning model with long-context and tool-use capabilities
|
Audience
Developers and AI teams in need of a solution with robust instruction following and RAGβenabled document processing for realβtime applications
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
$0.1 per 1M tokens
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationAnt Group
Founded: 2014
China
ant-ling.com
|
Company InformationUpstage AI
Founded: 2020
United States
www.upstage.ai/blog/en/introducing-solar-mini-compact-yet-powerful
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Claude Code
Hermes Agent
Hugging Face
Kilo Code
Llama 2
Mistral 7B
OpenClaw
OpenRouter
Syn
Upstage AI
|
Integrations
Claude Code
Hermes Agent
Hugging Face
Kilo Code
Llama 2
Mistral 7B
OpenClaw
OpenRouter
Syn
Upstage AI
|
|||||
|
|
|