Unverified50% confidenceBenchmarkExact time
According to hands-on information shared by a Bilibili creator, on a hardware platform with 128G unified memory, 873G bandwidth, and 2070 TOPS of compute, a Qwen 30B-class model achieved over 100 TPS in a single stream on coding tasks.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/21/2026
First Seen
Valid until: 11/4/2026
Sources
Related Entities
Related Claims
UnverifiedThe program recommends context length based on VRAM: 8 GB VRAM is recommended for a 32K context, and 24 GB VRAM can support 128K.74% similarUnverifiedA 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 testing73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1082228API
curl https://kongchang.com/api/v1/knowledge/claims/1082228MCP
get_claim(id=1082228)