1 points | by llmpath an hour ago
1 comments
Built this to solve local GPU VRAM sizing and real-time token cost calculations across 463+ models without paywalls or signups. Would love any feedback on GPUs or formulas to add!
Built this to solve local GPU VRAM sizing and real-time token cost calculations across 463+ models without paywalls or signups. Would love any feedback on GPUs or formulas to add!