Unverified50% confidenceFactExact time
The Agent's default self-hosted configuration uses the Qwen3.6-35B-A3B model with 4-bit quantization deployed via sglang.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedThe application has a built-in qwen3 4b model to enable out-of-the-box functionality79% similarUnverifiedTev1-4B-experimental is built on top of the Qwen3.5 4B base model.75% similarUnverifiedSeries such as Qwen2.5 and Gemma3 have already released 1B–3B quantized versions optimized specifically for edge scenarios.73% similarUnverifiedQwen3.5-4B can run efficiently on a single consumer-grade GPU (such as the RTX 4090), and after quantization can even be deployed on edge devices.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984717API
curl https://kongchang.com/api/v1/knowledge/claims/984717MCP
get_claim(id=984717)