Llama 3 8B Lunaris
Sao10K · Open weights · Released Aug 13, 2024 · sao10k/l3-lunaris-8b
8K contextStructured outputOpen weights
Available from 3 providersUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.04 | $0.05 | — | 8K | bf16 | 1s | 19 tok/s | 99.9% | |
| $0.04 | $0.05 | — | 8K | fp8 | 0.15s | 88 tok/s | 100.0% | |
| $0.05 | $0.05 | — | 8K | bf16 | 0.27s | 82 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago
About
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....
Specifications
Context window8,192
Max output16,384
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedAug 13, 2024
Knowledge cutoff2023-12-31
TokenizerLlama3
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/sao10k/l3-lunaris-8b)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks43 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.