Unverified50% confidenceFactExact time
在M2 Ultra（最高192GB统一内存）上，MLX可流畅运行700亿参数量级的模型
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
UnverifiedThe M3 Max is equipped with up to 128 GB of unified memory, capable of running unquantized 70B and even larger models, far exceeding the maximum 24 GB limit of consumer-grade NVIDIA graphics cards.73% similarUnverifiedA model with 70 billion parameters (70B) can run on a single RTX 4090 (24GB VRAM) after quantization.71% similarVerifiedThe unified memory bandwidth of the M3 Max chip is as high as 400GB/s, far exceeding the approximately 64GB/s of a traditional PCIe bus71% similarUnverifiedMiniMax M3 has a maximum context window of 1 million tokens, with a minimum guaranteed context of 512,000 tokens.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/535604API
curl https://kongchang.com/api/v1/knowledge/claims/535604MCP
get_claim(id=535604)