The last model of the Qwen-Next series, whose architecture is used for Qwen3.5. This is a capable (and fast) coding model with just 3B active parameters.
Specs
Params80B (3B active)
LicenseApache-2.0
Tags
Similarity · VAIL
VAIL Fingerprint
0024:002b:0039:005a:009a:0196:041a:5a55
Explore other models with behavioral similarity to Qwen3-Coder-Next.
Capability · Artificial Analysis
AA Index
21.3
Months Behind Frontier
13.8 mo
o1
05 Dec 2024
Adoption · Hugging Face
RAM score
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Hugging Face Downloads
513.8K
last 30d
6.2M
all time
HF Likes
1.6K
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Inference · OpenRouter
Tokens/Day
—
below top 50 this week
Peak Tokens/Day
23.8B
19 Mar 2026
Peak Rank
#25
06 Feb 2026
OpenRouter publishes daily token totals for its ~50 most-served models. Days missing from the chart mean Qwen3-Coder-Next 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
