Skip to main content
ModelLLMsv1.0

SOLAR 10.7B

by Upstage · open-source · Last verified 2026-03-17

Upstage's model created through a novel depth up-scaling technique that merges two pretrained models by removing intermediate layers. Achieves performance comparable to much larger models while maintaining efficient 10.7B parameter inference.

https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
D
DPoor
Adoption: DQuality: BFreshness: DCitations: CEngagement: F

Specifications

License
Apache 2.0
Pricing
open-source
Capabilities
text-generation, instruction-following, reasoning, depth-upscaling, efficient-inference
Integrations
huggingface, ollama, vllm, llama-cpp
Use Cases
general-chat, instruction-following, text-generation, fine-tuning-base
API Available
Yes
Parameters
10.7B
Context Window
4K tokens
Modalities
text
Training Cutoff
Mid 2023
Tags
llm, open-source, depth-upscaling, upstage, efficient
Added
2026-03-17
Completeness
85%

Index Score

36.4
Adoption
35
Quality
62
Freshness
38
Citations
40
Engagement
0

Explore the full AI ecosystem on Agents as a Service