Llama 3 8B Lunaris
by Sao10Ktext->text2 endpoints
Neura Intelligence Index
43.8/ 100
Rank
#225—
Confidence
mediumBenchmarks
7(18% coverage)
Overview
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....
Capabilities
Text generation
Structured output
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
8.2K tokens
Max Output
7.4K tokens
Knowledge Cutoff
2023-12-31
Tokenizer
Llama3
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
December 17, 20241y
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p
Benchmark Performance
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 41 | verified |
math
| Benchmark | Score | Source |
|---|---|---|
| FrontierMath | 5.5 | verified |
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 78 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| MMMU | 77.6 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| TAU-Bench Retail | 70.8 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.04
Output$0.05
Added
August 13, 2024
Last synced 11/6/2026