While Qwen2.5 VL is not new, the 32B version was missing. The outputs from this model differ from the rest of the series, being more focused on reasoning. This brings the performance close to the 72B version.
Specs
Params32B
LicenseApache-2.0
Similarity · VAIL
VAIL Fingerprint
003c:004d:0062:0078:00d2:01da:0709:5fbc
Explore other models with behavioral similarity to Qwen2.5-VL-32B-Instruct.
Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.31×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
1.5M
last 30d
11.5M
all time
HF Likes
499
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Inference · OpenRouter
Tokens/Day
—
below top 50 this week
Peak Tokens/Day
1.8B
29 Aug 2025
Peak Rank
#40
29 Aug 2025
OpenRouter publishes daily token totals for its ~50 most-served models. Days missing from the chart mean Qwen2.5-VL-32B-Instruct fell below that cutoff — not zero usage. OpenRouter logs usage separately per dated model version and per variant (like ":free"); the hub combines provider variants while keeping separately cataloged releases distinct.
Related Models
