MDL
Llama-3.2-1B
meta-llama
Parameters
1B
Downloads
1.8M
on HF
Likes
2.5K
Avg score
—
Weights
Open
Released
Sep 18, 2024
About
Llama-3.2-1B is a 1B-parameter open-weights model in the Llama family from meta-llama.
llama3.2text-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →The Carbon Footprint of Machine Learning Training Will Plateau, Then ShrinkSpinQuant: LLM quantization with learned rotationsOff-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning▲ 7 on HF · Jun 1, 2026Unextractable Protocol Models: Collaborative Training and Inference without Weight MaterializationMay 22, 2026X-Token: Projection-Guided Cross-Tokenizer Knowledge DistillationMay 20, 2026Representation Without Reward: A JEPA Audit for LLM Fine-TuningMay 14, 2026BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight QuantizationMay 11, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.