Expired50% confidenceFactExact time
Early LLaMA-2 only supported a 4K token context, whereas new-generation models such as DeepSeek-V3 and Qwen2.5 have extended the context to 128K or even longer.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/6/2026
First Seen
Valid until: 10/4/2026(expired)
Sources
Getting Started with Ollama: The Go-To Tool for Free Local LLM Deployment
bilibiliMia搞LLM7/1/2026
Related Claims
UnverifiedModels in the 3B–4B range, such as Qwen2.5 3B or Llama 3.2 3B, require only 2 to 2.5GB of VRAM under Q4 quantization.70% similarUnverifiedQwen3 在训练时支持长达 128K tokens 的上下文69% similarUnverifiedQwen 3.6 supports 256K ultra-long context.69% similarUnverifiedThe Qwen3.6 27B parameter version supports a maximum context window of 128K.68% similarVerifiedThe Qwen series models support context windows ranging from 8K to 128K.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/118894API
curl https://kongchang.com/api/v1/knowledge/claims/118894MCP
get_claim(id=118894)