SOLAR models
6 SOLAR models on Hugging Face, from 10.7B to 250.3B parameters. At the precision each one is published in, the smallest needs about 24.0 GB of VRAM (SOLAR-10.7B-Instruct-v1.0, cheapest live fit: RTX A5000) and the largest about 559 GB (Solar-Open2-250B, cheapest live fit: RTX PRO 6000). The cheapest way to run SOLAR-10.7B-Instruct-v1.0 is $0.176/hr.
SOLAR models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| SOLAR-10.7B-Instruct-v1.0 | 10.7B | F16 | 24.0 GB | RTX A5000 | $0.176/hr |
| SOLAR-10.7B-v1.0 | 10.7B | F16 | 24.0 GB | RTX A5000 | $0.176/hr |
| YanoljaNEXT-EEVE-Instruct-10.8B | 10.8B | BF16 | 24.2 GB | RTX 4080 Super | $0.338/hr |
| solar-pro-preview-instruct | 22.1B | BF16 | 49.5 GB | A100 | $1.21/hr |
| Solar-Open-100B | 102.7B | BF16 | 229 GB | RTX A6000 × 5 | $1.81/hr |
| Solar-Open2-250B | 250.3B | BF16 | 559 GB | RTX PRO 6000 × 6 | $8.25/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
