Unverified50% confidenceBenchmarkExact time
In a 3D game building test on an Apple M3 Ultra with 512GB unified memory, Qwen 3.8 completed it in one shot, while Ornith 1.5 required 6 separate iterations to barely approach the same level.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedAfter being quantized to 4-bit precision via tools such as Ollama, the 14B parameter version of Qwen3 can run smoothly on consumer-grade GPUs.63% similarUnverifiedOrcaRouter released the Qwen3.8-27B uncensored model card, claiming to have verified normal vLLM startup, available reasoning capabilities, multi-turn tool calling, and vision capabilities62% similarUnverifiedThe Ornith AI team released three open-source models in the Ornith 1.5 series, covering three parameter scales: 9B, 35B-A3B, and 397B.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907312API
curl https://kongchang.com/api/v1/knowledge/claims/907312MCP
get_claim(id=907312)