MDL
Qwen3-8B
unsloth
Parameters
8B
Downloads
79K
on HF
Likes
16
Avg score
—
Weights
Open
Released
Apr 28, 2025
About
Qwen3-8B is a 8B-parameter open-weights model in the Qwen3 family from unsloth.
apache-2.0text-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →YaRN: Efficient Context Window Extension of Large Language ModelsFunction-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models▲ 108 on HF · Jul 14, 2026KVpop -- Key-Value Cache Compression with Predictive Online Pruning▲ 23 on HF · Jul 6, 2026Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads▲ 19 on HF · Jul 1, 2026MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning▲ 13 on HF · Jul 13, 2026Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding▲ 12 on HF · Jul 7, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.