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
UnverifiedOn high-performance laptops, quantized Gemma models can achieve token generation speeds of 20–50 tokens per second; pure CPU inference is approximately 5–15 tokens/second, and INT4 quantization on NVIDIA RTX 4060/4070 can boost inference speed by 3–5 times.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% similarUnverifiedWhen running at 1-bit precision on an M2 Max equipped with 96GB of VRAM, generation speed for simple tasks is consistently around 28–30 tokens/second71% 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)