Model Anatomy See what's inside open-weight AI models

Can I run LFM3-1.7B on a Mac with 64 GB?

Yes

Its published weights (3.46 GB) fit in the 48.0 GB a Mac with 64 GB can use, with room for ≈ 256K tokens of context.

Full analysis of LFM3-1.7B Everything that runs on Mac with 64 GB Get the weights on Hugging Face
hf download LiquidAI/LFM3-1.7B

Files and context on Mac with 64 GB

Each file of LFM3-1.7B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn Mac with 64 GB Context (16-bit)Context (8-bit)
As published3.46 GBFits256K256K
BF16LiquidAI/LFM3-1.7B-GGUF3.47 GBFits256K256K
F16LiquidAI/LFM3-1.7B-GGUF3.47 GBFits256K256K
Q8_0LiquidAI/LFM3-1.7B-GGUF1.85 GBFits256K256K
Q6_KLiquidAI/LFM3-1.7B-GGUF1.43 GBFits256K256K
LFM3-1.7B-NVFP4LiquidAI/LFM3-1.7B-GGUF1.28 GBFits256K256K
Q5_K_MLiquidAI/LFM3-1.7B-GGUF1.26 GBFits256K256K
Q4_K_MLiquidAI/LFM3-1.7B-GGUF1.10 GBFits256K256K
Q4_0LiquidAI/LFM3-1.7B-GGUF1.05 GBFits256K256K
Q8_0AtomicChat/LFM3-1.7B-GGUF1.85 GBFits256K256K
Q6_KAtomicChat/LFM3-1.7B-GGUF1.59 GBFits256K256K
Q5_K_MAtomicChat/LFM3-1.7B-GGUF1.31 GBFits256K256K
Q4_K_MAtomicChat/LFM3-1.7B-GGUF1.13 GBFits256K256K
IQ4_XSAtomicChat/LFM3-1.7B-GGUF1.09 GBFits256K256K
IQ3_SAtomicChat/LFM3-1.7B-GGUF922 MBFits256K256K

LFM3-1.7B on other hardware

Popular models that run on Mac with 64 GB

Assumes 75% of the Mac's memory is usable (macOS's default limit for the GPU; it can be raised) and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.