Unverified50% confidenceReleaseExact time
Ant Ling released the native multimodal model Ling 3.2-Flash, with 560B total parameters and 25B activated per token.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/8/2026
First Seen
Valid until: 2/6/2027
Sources
Related Entities
Related Claims
UnverifiedAnt Group's Ling large model officially open-sourced Ling 3.1 Flash, with 560B parameters, about 25B activated, and a context window of up to 1 million.77% similarUnverifiedLing-3.1-flash activates only approximately 25 billion (~25B) parameters per token.73% similarUnverifiedIn a fair 4-bit comparison, MLX with D-Flash 2 speculative decoding ran at 16.6 tokens/s, versus Ollama Q4's 5.7 tokens/s.60% similarUnverifiedFlashProve performs proof generation for the Llama 4 Maverick model on a single H100 GPU, achieving a throughput of 110 tokens/second with a proof size of 19 MB.60% similarUnverifiedMiniMax M3.1 Flash uses a MoE architecture with approximately 428B total parameters and approximately 23B activated per token.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1147332API
curl https://kongchang.com/api/v1/knowledge/claims/1147332MCP
get_claim(id=1147332)