Unverified50% confidenceBenchmarkExact time
Qwen3.5 with approximately 800 million parameters achieved the fastest generation speed, approaching 15 tokens per second, with the second-place LFM2.5 exceeding 10 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedQwen3 27B's local inference speed is approximately 10 tokens per second.78% similarUnverifiedThe Q4_K_M/GGUF version of Qwen 27B decodes at approximately 10.7 tok/s on the same machine, roughly 1/3.8 of the MLX version.74% similarUnverifiedAfter INT4 quantization, the Qwen3-0.6B model file is only about 400 MB, retains approximately 95% of baseline capability, and an ordinary laptop CPU can achieve a generation speed of 10–30 tokens per second.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977938API
curl https://kongchang.com/api/v1/knowledge/claims/977938MCP
get_claim(id=977938)