Expired50% confidenceFactExact time
The nine checkpoints consist of four target models (Qwen3's 4B, 8B, 14B, and Gemma 4's 12B) multiplied by three algorithms
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/23/2026(expired)
Sources
Related Claims
UnverifiedThe Qwen3.6 35B model contains 256 experts, with each token activating only 8 routed experts and 1 shared expert, resulting in approximately 3B activated parameters during actual inference.67% similarUnverifiedIn a complex task test involving the generation of a visualization HTML for six sorting algorithms, Gemini 3.1 and Qwen 3.5 400B succeeded, while the local version of QwenCoder 80B failed.67% similarUnverifiedIn actual testing using the Qwen3 27B Q4 quantized dense model, the generation speed with thinking mode disabled is approximately 58–60 tokens/s.65% similarUnverifiedQwen3 is available on Ollama in multiple sizes including 0.6B, 1.7B, 4B, and 8B64% similarUnverifiedQwen 3.6 35B A3B has a clear advantage over Gemma 4 and Qwen 3.5 in long-context memory benchmarks.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/615363API
curl https://kongchang.com/api/v1/knowledge/claims/615363MCP
get_claim(id=615363)