Expired65% confidenceBenchmarkExact time
Qwen3 27B running on the DGX Spark can stably achieve 20–30 tokens/second.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
8/22/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/5/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedRunning the Qwen3.6 27B model on a GPU with 24 GB of VRAM, the generation speed reaches approximately 40 tokens per second without optimization, and 50–60 tokens/s after optimization.72% similarUnverifiedThe Qwen3.6 35B model achieved a generation speed of 86.7 tokens/s on oMLX with MTP technology, with a prompt processing speed of 1,735 tokens/s.69% similarUnverifiedOn the RTX 5090, the Qwen3.6 35B-A3B achieves an inference speed of 220 tokens/s with approximately 23 GB of VRAM usage.64% similarUnverifiedIn benchmark testing, Qwen3 27B achieved a generation speed of approximately 40-something tokens per second on 4 modified 2080 Ti cards without NVLink enabled.64% similarUnverifiedQwen3.6 27B supports a context length of 262K, and the 34B 80-layer version maintains the same context length unchanged64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/787048API
curl https://kongchang.com/api/v1/knowledge/claims/787048MCP
get_claim(id=787048)