Unverified50% confidenceFactExact time
The MiniCPM-2B model supports a 131K context
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/15/2026
First Seen
Valid until: 12/14/2026
Sources
Related Entities
Related Claims
UnverifiedA UP host running MiniCPM 2B with an RTX 4080S (16GB VRAM) + 64GB RAM configuration achieved an inference speed of approximately 110 tokens/second in real-world testing69% similarUnverifiedThe latest model's context length has reached 128K tokens.66% similarUnverifiedGroq's LPU-architecture-based service can compress the TTFT of mainstream 70B-class models to under 200ms, whereas the TTFT of general cloud services is typically between 500ms and 2s.65% similarUnverifiedThrough tensor parallelism, 2×H100 can run a 70B model at FP16 precision smoothly and support relatively high concurrency.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/923499API
curl https://kongchang.com/api/v1/knowledge/claims/923499MCP
get_claim(id=923499)