community pool / model answer

Qwen3.5-4B

chat · Qwen/Qwen3.5-4B

61 tok/s · model median · 20 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
AMD Ryzen 7 8745H w/ Radeon 780M	4-bit	28 tok/s	measured	1,537	3.5 GB	65,536	llama.cpp
AMD Ryzen 7 8745H w/ Radeon 780M Graphics	4-bit	22 tok/s	reported	961	- GB	65,536	llama.cpp
Intel(R) Core(TM) Ultra 7 155H	4-bit	14.6 tok/s	reported	-	- GB	2,048	llama.cpp
GTX 1650 4GB	4-bit	30.6 tok/s	reported	14,583	- GB	4,096	llama.cpp
RTX 3060 12GB	4-bit	76.5 tok/s	measured	1,124	- GB	131,072	llama.cpp
RX 6700 10GB	4-bit	76.6 tok/s	reported	2,141	4 GB	4,096	llama.cpp
Ryzen AI Max 395 128GB	4-bit	61.3 tok/s	measured	-	4.3 GB	32,768	llama.cpp
Ultra 7 155H 32GB	4-bit	12 tok/s	reported	-	- GB	2,048	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.