Unverified50% confidenceFactExact time
V4.1 Flash reduced compute by close to half during the Preview phase.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedCompared to 3.5 Flash, 3.6 Flash reduces average output tokens by approximately 17%, with some code tasks seeing reductions of up to 65%.76% similarVerifiedCompared to the previous generation Flash, V4.1 Flash's high-bandwidth memory requirements have been reduced to 1/4, and solid-state storage requirements have been reduced to 1/8.75% similarVerifiedV4 Flash's cache size is only 7% of that of V3.2.71% similarUnverifiedAfter compression, the DeepSeek V4 Flash model size was reduced from nearly 500 GB to 80.8 GB.67% similarUnverifiedV4.1 Flash is much smaller in scale compared to contemporaneous competitors at the 2.8 trillion parameter level (such as Kimi K3-tier models).67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995621API
curl https://kongchang.com/api/v1/knowledge/claims/995621MCP
get_claim(id=995621)