Unverified50% confidenceBenchmarkExact time
On a single CPU thread, Largha-150M-v1 takes about 1.64 seconds to process one case (one state plus five questions); with 8 threads, about 8–20 decisions/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedA 3-billion-parameter Llama takes 1 to 3 seconds per call on CPU, while a 70B model takes 40 seconds per call.75% similarUnverifiedTested on the same machine equipped with a Spark CPU and limited to three threads, Laya's median call latency was 541 milliseconds and Kev's was 756 milliseconds, with the 95th percentile at approximately 607 and 802 milliseconds respectively.72% similarUnverifiedWhen running IQ3_XXS quantized models with llama.cpp, the output speed is only 15 tok/s with prompt processing at 100–120 tok/s, while a self-developed engine brings the same quantization up to approximately 65 tok/s output and 430 tok/s prompt processing, representing close to a 4x performance improvement.72% similarUnverifiedThe first full run took 22.9 seconds, 12 parallel Jev calls completed in about 1.1 seconds, and the main performance bottleneck was Postgres queries of about 700ms each that also had to queue.72% similarUnverifiedRunning a 27B model on M1 Max with a 32,000-token prompt requires waiting more than 500 seconds before the first character is output, whereas the M5 Max takes less than one minute (approximately 40 seconds with optimized software).71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016983API
curl https://kongchang.com/api/v1/knowledge/claims/1016983MCP
get_claim(id=1016983)