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
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedQwen3.8-27B's output speed is 55.1 tokens/second, and Ornith 1.5's is 90.4 tokens/second.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% similarUnverifiedWhen running at 1-bit precision on an M2 Max equipped with 96GB of VRAM, generation speed for simple tasks is consistently around 28–30 tokens/second72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041084API
curl https://kongchang.com/api/v1/knowledge/claims/1041084MCP
get_claim(id=1041084)