Unverified50% confidenceFactExact time
The generation speed officially given for 2.5-24 is 184 characters per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedCompared with the full-rank (no low-rank approximation) approach, VPU at dim=256 reduced 200 steps from 4249ms to 160ms, achieving a 26.44x speedup.69% similarUnverifiedThe UP host tested MiniCPM-2B on a computer with 4G VRAM and achieved a generation speed of 57 tokens per second, with a first-token latency of only 0.22 seconds.69% similarUnverifiedIn BF16 configuration (two 48GB GPUs), decoding speed ranges from 25.1 tok/s at 1K to 23.9 tok/s at 128K, with almost no degradation.69% similarUnverifiedIn the test, model loading took only a few seconds, GPU usage dropped from 23GB to about 17GB, the first test prompt processing took 225ms, generation speed was stable at 33.5 tok/s, with a total output of 1500 tokens.68% similarUnverifiedOn GSM8K, OQ4E took 2,450.2 seconds, while 8-bit took as long as 5,471.2 seconds, more than twice the time.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1035432API
curl https://kongchang.com/api/v1/knowledge/claims/1035432MCP
get_claim(id=1035432)