family member

Qwen 3 VL-8B

1 build of Qwen 3 VL-8B measured on real machines — different packagers, precisions and engines, each a different file with its own numbers. The best each engine proved is first; every build has its own page with the machines and signatures behind it.

on ollama · 1 build

trained 256K · proved 128K context proved by Qwen F16

3.8 tok/s peak, by Qwen F16

proved by at least one build: Tool calling · Faithful to tool results · Structured output · Sustained output · Vision · Counts in images · Multiple images at once · Spatial reasoning · Writes code · Follows instructions

build	publisher	precision	engine	whose work	context proved	best tok/s	machines
hf.co/Qwen/Qwen3-VL-8B-Instruct-GGUF:F16	Qwen	F16	ollama	vendor	1,31,072	3.8	1

derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

Qwen3-VL-8B-Instruct-abliterated-v11 build measured