The small MoE model also gets the same treatment as the large model: A split into a reasoning and non-reasoning version, 1M context and a performance boost across the board.
Specs
Params30B
LicenseApache-2.0
Tags
Similarity · VAIL
VAIL Fingerprint
0014:001a:0030:0039:0063:00f0:02fa:5acb
Explore other models with behavioral similarity to Qwen3-Coder-30B-A3B-Instruct.
Resources
Capability · Artificial Analysis
AA Index
13.6
Months Behind Frontier
10.6 mo
o1-preview
12 Sep 2024
Adoption · Hugging Face
RAM score
—
Hugging Face Downloads
1.5M
last 30d
14.1M
all time
HF Likes
1.2K
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Inference · OpenRouter
Tokens/Day
—
below top 50 this week
Peak Tokens/Day
28.6B
08 Oct 2025
Peak Rank
#5
08 Oct 2025
OpenRouter publishes daily token totals for its ~50 most-served models. Days missing from the chart mean Qwen3-Coder-30B-A3B-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
