← All models

Qwen · Last 7 days

Qwen3.5-9B

0–100 · higher means more positive community experience, not benchmark performance.

Updated 2026-09-05 14:21 UTC · 2026-08-29 – 2026-09-05 UTC
Community score58.7/10010 comments in 7 days

Community reviews

Selected comments from the last 7 days. The balance of excerpts does not represent the share of positive reviews.

8 selected excerpts

NegativeCoding

“Qwen will offer backups and printouts but always has 1-3 errors”

PositiveSpeed & latency

“I can have fun chats with Qwen3.5-9b and anything smaller”

PositiveSpeed & latency

“I get around 100-200 t/s with qwen3.5-9b combined with dflash. Is it really worth switching? I'm kinda skeptical”

NegativeCoding

“It's legit better than Qwen3.5 9b in coding”

PositiveGeneral text

“You can even drop vision to save space on the 3090 and enable it on the 9b model which is very capable in my experience and allows for more context in the 3090”

PositiveImage / vision

“The same chart run through qwen3.5-9b was exact and read all values. So I swapped back just in case.”

NegativeCoding

“7B seems to beat qwen 3.5 9b in coding while matching or falling slightly short in other areas according to there benchmarks”

PositiveReasoning

“scores well on bs bench, which means it's less likely to constantly agree with you even if you're talking nonsense”