Unverified50% confidenceFactExact time
DeepSeek-V4.1-Flash-1017 supports a 1 million token context, with a recommended maximum output of 256K or more.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedDeveloper Soto wrote his own inference engine and ran the 552B-parameter DeepSeek V4.1 Flash on a gaming PC with a single 24G RTX 4090, 90G of memory plus NVMe storage, measuring about 27 tokens/s decoding and 180-320 tokens/s prefill.76% similarUnverifiedAccording to community discussions, the DeepSeek-V4.1-Flash model's 1 million token context window occupies only approximately 900 MB of VRAM.76% similarUnverifiedAccording to community-cited information, DeepSeek-V4.1-Flash has 552B backbone parameters, 196B Engram parameters, and safetensors weight files totaling approximately 350 GB.76% similarUnverifiedThe DeepSeek Flash model can output more than 100 tokens per second.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059982API
curl https://kongchang.com/api/v1/knowledge/claims/1059982MCP
get_claim(id=1059982)