Unverified50% confidenceBenchmarkExact time
On Qwen3.5-397B-A17B, TokenSpeed reported speeds of up to 580 tokens/second on agent workloads.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedQwen3.8-27B的输出速度为55.1 tokens/秒，Ornith 1.5为90.4 tokens/秒。77% similarVerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.75% similarUnverifiedOn the test machine, Qwen3-Next-80B reads a 1024-token prompt at 62 tok/s and writes at 24 tok/s without the draft enabled; Qwen3-Coder-Next, also 48.4GB, reads at 66 and writes at 22.74% similarUnverified在配备96GB显存的M2 Max上以1-bit精度运行时，简单任务生成速度稳定在约28-30 tokens/秒72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041084API
curl https://kongchang.com/api/v1/knowledge/claims/1041084MCP
get_claim(id=1041084)