Unverified50% confidenceFactExact time
Strands Decider 2B is based on Qwen3.5-2B plus a pointer head and LoRA, uses the Apache-2.0 license, has about 4.5GB of weights, and produces calibrated typed answers through a single forward pass.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedQwen 3.6（Qwen3-30B-A3B）采用混合专家架构，总参数约300亿，激活参数约36亿，以Apache 2.0协议开源66% similarUnverifiedQwen3-Coder 30B uses a Mixture-of-Experts (MoE) architecture, activating only approximately 3.3 billion parameters per inference, but the download package contains the full model weights.60% similarPartially VerifiedQwen3.8-Flash-Next adopts a Mixture of Experts (MoE) architecture with 125B total parameters and 6B activated parameters.59% similarUnverifiedSeries such as Qwen2.5 and Gemma3 have already released 1B–3B quantized versions optimized specifically for edge scenarios.59% similarUnverifiedQwen2.5 7B Instruct excels in code and tool invocation, and the Qwen2.5 series has native support for Function Calling.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011788API
curl https://kongchang.com/api/v1/knowledge/claims/1011788MCP
get_claim(id=1011788)