How much RAM does granite-timeseries-patchtst-fm-r2 need?

granite-timeseries-patchtst-fm-r2 needs about 797 MB of memory at Q4_K_M quantization with 4K context. The download itself is 232 MB; the extra covers the context cache and runtime overhead.

Can I run granite-timeseries-patchtst-fm-r2 on a laptop?

Yes — it runs comfortably on a machine with 8GB RAM, for example Base MacBook Air (M1/M2).

granite-timeseries-patchtst-fm-r2: hardware requirements

granite-timeseries-patchtst-fm-r2 needs about 797 MB of memory at Q4 quantization — a 232 MB download plus room for context and overhead. That fits a machine with 8GB RAM.

Parameters

385M

Tier

Runs on a laptop

Licence

See model card

Released

2026-09-09

Will it run on your machine?

8GB RAMRuns well 16GB RAMRuns well 24GB RAMRuns well 32GB RAMRuns well 64GB RAMRuns well 128GB RAMRuns well 8GB VRAMRuns well 12GB VRAMRuns well 16GB VRAMRuns well 24GB VRAMRuns well 32GB VRAMRuns well

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

Quant	Download	RAM @ 4K	RAM @ 32K	Source
Q4_K_Mrecommended	232 MB	797 MB	797 MB	estimated
Q5_K_M	273 MB	842 MB	842 MB	estimated
Q6_K	315 MB	890 MB	890 MB	estimated
Q8_0	409 MB	995 MB	995 MB	estimated
BF16	769 MB	1.4 GB	1.4 GB	estimated

“Measured” sizes are read from published GGUF files. “Estimated” sizes are derived from the parameter count and are typically within a few percent. The RAM columns add the context cache and runtime overhead to the download size.

Model card on HuggingFace →API specs & pricing →Verified 2026-09-10Tracked for 12 months after release