Qwen3-VL
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
0warn against
Nov 30, 2025first mention
Aug 6, 2026latest mention
Why people recommend it
“Qwen3-VL picks up new images in a NAS, auto captions and adds the text descriptions as a hidden EXIF layer”
“I generally run Qwen3-vl at 235b, at a Q4_K_M quantization level so that it fits”
runs a 256GB M3 Ultra Mac Studioon “Ask HN: Anyone Using a Mac Studio for Local AI/LLM?”
Show 1 more
“i use qwen-30b-vl all the time locally as my goto model because it's just so insanely fast”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Who recommends it in their own words
Threads where it came up
- Qwen3-VL can scan two-hour videos and pinpoint nearly every detail 2 mentions
- Qwen3.8 Max now ranked as the best overall model by agentic index 1 mention
- Show HN: Qwen 3.5 running on a $300 Android phone – on-device, open source 1 mention
- Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs 1 mention
- Ask HN: Anyone Using a Mac Studio for Local AI/LLM? 1 mention
- Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs 1 mention
Data: qwen3-vl.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 7
“Qwen3-VL picks up new images in a NAS, auto captions and adds the text descriptions as a hidden EXIF layer”
“Vision uses SmolVLM and Qwen3-VL.”
“I built a 1000+ line Python pipeline using Qwen3-VL to analyze each film with subtitles enabled.”
“I generally run Qwen3-vl at 235b, at a Q4_K_M quantization level so that it fits”
“I built a 1000+ line extraction pipeline using Qwen3-VL”
“Insane if true... now I wonder, if I use it to go through some old dance routing video catalogue”
“i use qwen-30b-vl all the time locally as my goto model because it's just so insanely fast”