community pool / model answer

LFM2.5-1.2B-Instruct

chat · LiquidAI/LFM2.5-1.2B-Instruct

120.7 tok/s · model median · 5 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
AMD Ryzen 7 7840HS	4-bit	74.8 tok/s	reported	-	- GB	2,048	llama.cpp
AMD Ryzen 7 8745H w/ Radeon 780M Graphics	8-bit	58.9 tok/s	reported	264	- GB	131,072	llama.cpp
RTX 3060 12GB	8-bit	231.2 tok/s	reported	334	2.7 GB	4,608	llama.cpp
RX 570 4GB	4-bit	120.7 tok/s	reported	24	- GB	2,048	llama.cpp
RX 6750 XT 12GB	4-bit	500 tok/s	reported	-	12.3 GB	64,000	llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.