Unverified50% confidenceBenchmarkExact time
Running via llama.cpp on a MacBook Pro with an M4 Pro chip and 24GB unified memory, the text decoding speed is 10.13 tokens/second, with each complete task taking 4 to 7 minutes.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedIn a controlled test, the 35B model ran at approximately 100 tokens/second (Mac Studio), roughly five times the 9B model's 16 tokens/second77% 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% similarUnverifiedSmall models (1B–7B parameters) used for text completion tasks can run smoothly on Macs with 8 GB or more of unified memory, with inference latency kept within a few hundred milliseconds.75% similarUnverifiedBased on the MLX framework, top-configured Mac models can achieve a generation speed of approximately 20 tokens/second when running the Llama-3-70B quantized model.74% similarUnverifiedIf the quantized model weights are 150 GB, reading the weights once at a bandwidth of 273 GB/s takes approximately 0.55 seconds, giving a theoretical single-token generation speed of approximately 1.8 tokens/s (excluding computation latency and cross-node communication overhead).72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/909121API
curl https://kongchang.com/api/v1/knowledge/claims/909121MCP
get_claim(id=909121)