Unverified50% confidenceBenchmarkExact time
A third-party same-VRAM comparison on Zhihu shows that Stratavie writes responses at 62.9 tokens/second, while Llama.cpp achieves 23.4 tokens/second, with long-document reading being nearly 10 times faster.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedWith a 32K prompt input, the Q2 quantization read speed can increase from 572 tokens/s to 1,290 tokens/s, and Q3 can increase from 383 to 1,208 tokens/s.65% similarUnverifiedUnder conditions of 2944 input tokens and 1024 output tokens, normal mode reaches 29.9 tokens per second, which improves to 48.4 tokens/s after enabling MTP2.64% similarUnverifiedIn Strata's speed table, under a 128k context, Q2_0 (2-bit) achieves 65.1 tokens/s and IQ2_XS achieves 52 tokens/s; under a 4k short context, IQ3_XXS achieves 65.6 tokens/s.64% similarUnverifiedStrata uses the model's built-in multi-token prediction layer for speculative decoding, drafting up to 3 tokens at a time and producing an average of 2.4 to 3.2 tokens per pass, with the output results unchanged.63% similarUnverifiedUnder a 15-minute time limit per problem, the proof agent achieved a successful proof rate of 34.9% (157/450) on StochBench.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1000746API
curl https://kongchang.com/api/v1/knowledge/claims/1000746MCP
get_claim(id=1000746)