Unverified90% confidenceFactTime unknown
Claude Haiku 4.5拥有20万token的上下文窗口和6.4万token的最大输出长度
1
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedClaude Haiku 4.5's processing speed can reach 100–200+ tokens per second74% similarUnverifiedBonsai is equipped with a 4-bit vision tower (approximately 0.5GB), supports a context window of approximately 262,000 tokens, and retains full multimodal agent capabilities62% similarUnverifiedQwen3-series coding models load at approximately 20 GB and can expand to 35–40 GB during inference.62% similarUnverifiedA ~25 GB Q3 model running entirely within the RTX 4090's VRAM (bandwidth ~1 TB/s) theoretically achieves ~40 tokens per second, whereas running it in DDR5 memory (~80 GB/s) drops throughput to 1–3 tokens per second.61% similarUnverifiedRunning the Qwen3.6 27B model on a GPU with 24 GB of VRAM, the generation speed reaches approximately 40 tokens per second without optimization, and 50–60 tokens/s after optimization.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/24311API
curl https://kongchang.com/api/v1/knowledge/claims/24311MCP
get_claim(id=24311)