Every AI leaderboard

28 leaderboards · 986 models ranked

Qwen3.5 4B specs, prices, where it runs and its benchmark standing

open weights · top 10 on 0 of 1 · released Mar 2, 2026

Facts

Provider
Alibaba
Release date
Mar 2, 2026
Boards
Parameters
4.7B total
Hugging Face
Modalities
Text, Image to Text
Hugging Face
License
Apache 2.0
Hugging Face
Hardware
Estimate: about 9.3 GB of weights as published (BF16), about 4.7 GB at 8-bit, about 2.3 GB at 4-bit, plus memory for the context
Hugging Face config
Weights
Open weights
Benchmarks
1 board captured
RankBoardScore
65MMLU-ProReasoning · stale since 2026-03-11 · as “Qwen3.5-4B”79.1%

Versions and release history

21 versions in this line since Sep 17, 2024, from Pricing, OpenRouter and the boards.

VersionReleased
Qwen3.8 27BAug 14, 20262 months ago
Qwen3.8 2.4T A95BAug 12, 20262 months ago
Qwen3.6 27BApr 22, 20266 months ago
Qwen3.6 35B A3BApr 14, 20266 months ago
Qwen3.5 4Bthis modelMar 2, 20268 months ago
Qwen3.5 27BFeb 25, 20268 months ago
Qwen3.5 122B A10BFeb 24, 20268 months ago
Qwen3.5 9BFeb 24, 20268 months ago
Qwen3.5-35B-A3BFeb 24, 20268 months ago
Qwen3.5 397B A17BFeb 13, 20268 months ago
Qwen3 30B A3BJul 30, 20251 year ago
Qwen3-235B-A22B-Thinking (Jul 2025)Jul 25, 20251 year ago
Category ranks, more models and catalog changes