Verified65% confidenceBenchmarkExact time
Under the M5 Ultra's 1.2 TB/s bandwidth, the theoretical speed of a 100 GB quantized model is approximately 12 tokens/s, a 200 GB model approximately 6 tokens/s, and a 300 GB model approximately 4 tokens/s.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
9/23/2026
First Seen
Valid until: 12/22/2026
Sources
Related Entities
Related Claims
UnverifiedA 70B-parameter model (140 GB of weights) has a theoretical maximum generation speed of approximately 7 tokens/second at 1 TB/s bandwidth.80% similarUnverifiedQuantprobe claims to enable a machine with only 6GB of VRAM and 16GB of RAM to run 30B-class models at 22 tokens/s.79% similarVerified128GB DDR5 memory can fully load all weights of a 70B-class model, but at a speed of approximately 2–5 tokens/s.76% similarUnverifiedIn a text generation test using an 8-billion-parameter model, the M5 Ultra achieved 188 tokens per second versus 129 tokens per second for the M3 Ultra, representing only 1.45x.76% similarUnverifieddecode阶段的生成速度近似等于内存带宽÷模型大小，例如在内存带宽273GB/s的M4 Pro上运行4GB的Q4量化7B模型理论最大生成速度约68 tokens/s76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945139API
curl https://kongchang.com/api/v1/knowledge/claims/945139MCP
get_claim(id=945139)