Unverified50% confidenceFactExact time
Smaller or older models such as Qwen Math Plus may have a context window of only approximately 4,000 tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedThe early Codex model had a context window of only approximately 4,000 tokens (roughly 3,000 English words)65% similarUnverifiedQwen3.5-4B is a small model with only 4 billion parameters, released by Alibaba's Tongyi Qianwen team.63% similarUnverifiedQwen3 27B natively supports a context of 262,000 tokens and can be extended to 1,000,000 tokens via YaRN extrapolation.62% similarUnverifiedQwen3 Max is Alibaba's flagship large model, with 2.4 trillion parameters and a 1 million token context window.61% similarUnverifiedRunning quantized models from the Qwen3 series on a Mac M3 Ultra, inference speed reaches approximately 34 tokens/s under Q8 quantization.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/892973API
curl https://kongchang.com/api/v1/knowledge/claims/892973MCP
get_claim(id=892973)