Expired50% confidenceBenchmarkExact time
On a 128GB MacBook Pro M3 Max, independent benchmarks show DS4 achieving a generation speed of 26.68 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/6/2026
First Seen
Valid until: 10/4/2026(expired)
Sources
284B大模型跑进MacBook：DeepSeek本地推理的真实突破与门槛
bilibili声译看世界7/3/2026
Related Claims
Unverified27B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/s79% similarUnverifiedThe test was conducted on a MacBook with 36GB of memory, with the model loaded at a 128K context size and Q8 KV cache.75% similarUnverifiedWhen running at 1-bit precision on an M2 Max equipped with 96GB of VRAM, generation speed for simple tasks is consistently around 28–30 tokens/second74% similarVerifiedThe M4 Max already supports 128 GB of unified memory73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/116895API
curl https://kongchang.com/api/v1/knowledge/claims/116895MCP
get_claim(id=116895)