community pool / model answer

Agents-A1-Q4_K_M-GGUF

chat · InternScience/Agents-A1-Q4_K_M-GGUF

74.6 tok/s · model median · 17 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
RTX 3060 12GB ×2	4-bit	91.7 tok/s	measured	3,126	20.9 GB	65,536	llama.cpp
RX 570 4GB	4-bit	8.7 tok/s	reported	644	- GB	2,048	llama.cpp
RX 570 4GB ×2	4-bit	16.4 tok/s	reported	174	- GB	2,048	llama.cpp
Ryzen AI Max 395 128GB	4-bit	62 tok/s	reported	46,678	- GB	262,144	llama.cpp
Ryzen AI Max 395 64GB	4-bit	74.6 tok/s	measured	1,592	20.4 GB	8,192	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.