Qwen2.5 is far from an insider tip anymore, the Coder models are a continuous pre-training on top of Qwen2.5, breaching the 20T threshold in the open model space for the first time.
Specs
Params32B
LicenseApache-2.0
Similarity · VAIL
VAIL Fingerprint
003b:0055:0086:00c1:0115:01a5:057e:5dea
Explore other models with behavioral similarity to Qwen2.5-Coder-32B-Instruct.
Resources
Capability · Artificial Analysis
AA Index
7.1
Months Behind Frontier
12 mo
gpt-4-turbo
06 Nov 2023
Adoption · Hugging Face
RAM score
—
Hugging Face Downloads
1.2M
last 30d
10.6M
all time
HF Likes
2.1K
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Inference · OpenRouter
Tokens/Day
—
below top 50 this week
Peak Tokens/Day
2B
13 Mar 2025
Peak Rank
#8
02 Jan 2025
OpenRouter publishes daily token totals for its ~50 most-served models. Days missing from the chart mean Qwen2.5-Coder-32B-Instruct fell below that cutoff — not zero usage. OpenRouter logs usage separately per dated model version and per variant (like ":free"); the hub sums them into one daily total per model.
Related Models
