Unverified50% confidenceFactExact time
Qwen3.8-Flash-Next has a 48-layer structure with 512 experts per layer and 180B-class parameters (125B main body + 51B N-gram table + 4B MTP).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedQwen3.8-Flash-Next has approximately 6B activated parameters.74% similarUnverifiedQwen3 is available on Ollama in multiple sizes including 0.6B, 1.7B, 4B, and 8B71% similarUnverifiedQwen2.5-72B approaches the performance of Llama-3.1-405B across multiple benchmarks.70% similarUnverifiedQwen3覆盖从0.6B到235B的完整参数矩阵70% similarUnverifiedQwen2.5-3B-Instruct, Phi-3.5-mini (3.8B), and Llama-3.2-3B-Instruct are the three models with the best overall performance at small parameter scales at the end of 2024.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978624API
curl https://kongchang.com/api/v1/knowledge/claims/978624MCP
get_claim(id=978624)