Unverified50% confidenceBenchmarkExact time
Calling Qwen3 27B within an Agent framework (Hornis/赫米) can maintain approximately 60 T/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/1/2026
First Seen
Valid until: 11/30/2026
Sources
Related Entities
Related Claims
UnverifiedIn this configuration, Qwen3 27B achieves approximately 70 T/s natively in llama.cpp, with a measured peak of 76 T/s.73% similarUnverifiedQwen3.6 27B supports a context length of 262K, and the 34B 80-layer version maintains the same context length unchanged73% similarUnverifiedQwen 4B and 7B versions can run smoothly on entry-level graphics cards with 8GB of VRAM such as the RTX 3060.68% similarUnverifiedAfter 4-bit quantization, Qwen-7B can run smoothly on a consumer-grade GPU with 24 GB of VRAM.67% similarUnverifiedThe original Qwen3 model supports a 256K context, but local deployment is limited to 128K due to VRAM constraints66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/837543API
curl https://kongchang.com/api/v1/knowledge/claims/837543MCP
get_claim(id=837543)