Maxime Labonne PRO

mlabonne

https://mlabonne.github.io/blog

AI & ML interests

Post-training, model editing, quantization

Recent Activity

updated a Space about 3 hours ago

mlabonne/trackio

published a Space about 3 hours ago

mlabonne/trackio

published a model 7 days ago

LiquidAI/LFM2.5-VL-450M-MLX-5bit

View all activity

Organizations

upvoted 6 articles about 2 months ago

Article

Kimi K2.5: Still Worth It After Two Weeks?

Feb 23

•

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

Feb 20

•

501

Article

Train AI models with Unsloth and Hugging Face Jobs for FREE

Feb 20

•

Article

Qwen3.5: Nobody Agrees on Attention Anymore

Feb 17

•

Article

MiniMax-M2.5: The $1/hour Frontier Model

Feb 17

•

Article

GLM-5: China's First Public AI Company Ships a Frontier Model

Feb 17

•

upvoted an article 2 months ago

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

Feb 4

•

upvoted 3 articles 3 months ago

Article

Why Your AI Strategy Needs Hugging Face Storage

Jan 26

•

Article

Open Responses: What you need to know

Jan 15

•

111

Article

SmolLM-Smashed: Tiny Giants, Optimized for Speed

Jan 13

•

upvoted 4 collections 3 months ago

upvoted a collection 4 months ago

Nemotron-Post-Training-v3

Collection

Collection of datasets used in the post-training phase of Nemotron Nano and Super v3. • 28 items • Updated about 15 hours ago • 121

upvoted an article 4 months ago

Article

New in llama.cpp: Model Management

Dec 11, 2025

•

130

upvoted a collection 4 months ago

NanoBEIR datasets

Collection

These datasets are compatible with the (Sparse)NanoBEIREvaluator with Sentence Transformers v5.2+. Also CrossEncoderNanoBEIREvaluator if bm25 column • 16 items • Updated Mar 2 • 16

upvoted a paper 4 months ago

LFM2 Technical Report

Paper • 2511.23404 • Published Nov 28, 2025 • 56

upvoted a collection 5 months ago

Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability

Collection

A compilation of sparse auto-encoders trained on large language models. • 37 items • Updated Dec 16, 2025 • 24

upvoted an article 5 months ago

Article

Continuous batching from first principles

Nov 25, 2025

•

357

Maxime Labonne PRO

AI & ML interests

Recent Activity

Organizations

mlabonne's activity

Kimi K2.5: Still Worth It After Two Weeks?

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

Train AI models with Unsloth and Hugging Face Jobs for FREE

Qwen3.5: Nobody Agrees on Attention Anymore

MiniMax-M2.5: The $1/hour Frontier Model

GLM-5: China's First Public AI Company Ships a Frontier Model

Community Evals: Because we're done trusting black-box leaderboards over the community

Why Your AI Strategy Needs Hugging Face Storage

Open Responses: What you need to know

SmolLM-Smashed: Tiny Giants, Optimized for Speed

New in llama.cpp: Model Management

Continuous batching from first principles