Unverified50% confidenceFactExact time
Ideator uses gemma-4-26b-a4b-it and then gemma-4-31b-it to run the agent loop and write the report.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedThe Agent's default self-hosted configuration uses the Qwen3.6-35B-A3B model with 4-bit quantization deployed via sglang.65% similarUnverifiedXingchen 4.0 29B is compatible with fine-tuning tools such as MindFormers and LLaMA-Factory, as well as inference frameworks such as SGLang and vLLM.62% similarUnverifiedMicrosoft-Decision-1 was built through post-training on Alibaba's Qwen3.5-9B60% similarUnverifiediFlytek open-sourced two small models of Spark X 2.5, the 4B and 1.7B, targeting edge-side agent scenarios, employing a hybrid attention architecture with native support for up to 1 million token context.60% similarUnverifiedThe working solution relies on a combination: DeepSeek provides the weights, coolbho3k does the 3-bit quantization, turboderp wrote the EXL3 format and the ExLlamaV3 inference library, Victor Cruz wrote the vllm-exl3 bridge layer, Diffbot designed the per-expert split scheme, startup flow and kernels, and InferenceKey did the integration and measurement.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1058897API
curl https://kongchang.com/api/v1/knowledge/claims/1058897MCP
get_claim(id=1058897)