Unverified50% confidenceBenchmarkExact time
In benchmark testing on an AMD RX 7900 GPU, Ornith 35B achieved an overall accuracy of 85% (18 out of 21 passed), a generation speed of 74 tokens/s, a prompt processing speed of 850 tokens/s, and a VRAM usage of 20 GB.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedGemma量化模型在高性能笔记本电脑上Token生成速度可达每秒20-50个，纯CPU推理约5-15 tokens/秒，INT4量化下NVIDIA RTX 4060/4070可将推理速度提升3-5倍74% similarUnverifiedLing 3.0 Tiny achieves an inference speed of approximately 86–90 tokens per second on a MacBook with M4 Pro, with a peak memory usage of approximately 8.34 GiB under an 8K context.72% similarUnverified在配备96GB显存的M2 Max上以1-bit精度运行时，简单任务生成速度稳定在约28-30 tokens/秒71% similarUnverifiedOrnith 35B (4-bit MLX) generates at approximately 100 tokens/second on a Mac Studio, nearly 5 times faster than the 9B on a Mac Mini.71% 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).71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/914948API
curl https://kongchang.com/api/v1/knowledge/claims/914948MCP
get_claim(id=914948)