Expired50% confidenceBenchmarkExact time
Qwen 3.5 9B (Q6_K) output at approximately 168 tok/s, faster than Bonsai 2 27B's 101 tok/s.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/18/2026
First Seen
Valid until: 10/2/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedQwythos-9B achieves a token output speed of approximately 75 tokens per second under Q8 quantization.76% similarVerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.73% similarUnverifiedQwen3 27B's local inference speed is approximately 10 tokens per second.72% similarVerifiedQwen2.5-Coder-32B running with Q4 quantization on an RTX 4090 can achieve an inference speed of 40–60 tokens per second.71% similarVerifiedIn benchmark testing, Qwen3 27B achieved a generation speed of approximately 40-something tokens per second on 4 modified 2080 Ti cards without NVLink enabled.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/933018API
curl https://kongchang.com/api/v1/knowledge/claims/933018MCP
get_claim(id=933018)