Unverified50% confidenceBenchmarkExact time
On an RTX 5070 with a 6-core Ryzen and 64 GB of memory, Strata achieves approximately 90 tokens/second for short conversations, approximately 67 tokens/second at a 128,000-token context, and approximately 1,300 tokens/second for reading prompts.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
VerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.71% similarUnverifiedAn older RTX 3090, thanks to its 24 GB VRAM accommodating more experts, is estimated to achieve 100 to 140 tokens/second running Strata, indicating that under this workload VRAM capacity outweighs raw floating-point compute.71% similarUnverifiedIn an RTX 5060 Ti 16GB + 64GB RAM environment, Qwen3 27B took 1 hour and 10 minutes to generate a responsive personal website, averaging 6.42 tokens per second.70% similarUnverifiedIn terms of prompt processing speed, the RTX 4090 achieves approximately 3,000 tokens/s and the M5 Max approximately 800 tokens/s, giving NVIDIA a clear advantage in long-document and codebase input scenarios.70% similarVerifiedAt a baud rate of 9600, UART can transmit approximately 960 bytes per second (each byte requires 10 bits: 1 start bit + 8 data bits + 1 stop bit).70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978620API
curl https://kongchang.com/api/v1/knowledge/claims/978620MCP
get_claim(id=978620)