Unverified50% confidenceBenchmarkExact time
The Gemma E6B small model achieved a measured speed of over 46 tokens/second on that mini PC.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/19/2026
First Seen
Valid until: 12/18/2026
Sources
Related Entities
Related Claims
UnverifiedThe Gemma 4 26B MOE version achieves an actual inference speed of 60 tokens per second on a GPU with 24GB of VRAM.74% similarUnverifiedOn high-performance laptops, quantized Gemma models can achieve token generation speeds of 20–50 tokens per second; pure CPU inference is approximately 5–15 tokens/second, and INT4 quantization on NVIDIA RTX 4060/4070 can boost inference speed by 3–5 times.69% similarUnverified在M4 Max上进行FP16精度测试，hy3d shape（small）任务运行时间20.9秒，峰值内存约5.6GB64% similarUnverified27B稠密模型在24GB M4 Pro Mac mini上使用4-bit量化可以运行，速度约为11 tok/s63% similarUnverifiedThe theoretical peak of a 56k dial-up modem is approximately 7KB per second.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/933717API
curl https://kongchang.com/api/v1/knowledge/claims/933717MCP
get_claim(id=933717)