cd/entity/llamabench.aiยท homeโ€บ entitiesโ€บ llamabench.ai
grep -l @llamabench.ai /news/*.json | wc -l โ†’ 1

llamabench.ai

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

01:00
2026-08-26
discuss.huggingface.co
artificial-intelligence

How many tokens will an old 3090 produce?

An RTX 3090 can generate about 40 tokens per second when running Qwen3.8-27B, according to crowd-sourced benchmarks from llamabench.ai and user reports. The 24 GB VRAM of the 3090 is sufficient for quโ€ฆ

// co-occurs with top 4 entities
// topics top 3 topics