LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
LiquidAI
• • 34Community Blog & Articles
Community Articles
view all
audiospeechbenchmark
Measuring benchmark optimization in speech recognition
- +3
29
August 21, 2026 
Up to 3.2x Faster Inference with LFM2.5-DSpark
28
August 20, 2026 
How Much Memory Does Your Agent Actually Need?
63
August 18, 2026 
nlpguidecommunity
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
86
August 18, 2026 
Same Cluster, 33 Points More Utilization: What Changed Was the Order
16
August 17, 2026 
researchcommunityhub
State of Open Models: Summer 2026 Observations
147
August 14, 2026 
Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
28
August 13, 2026 
researchcommunityagents
What We Learned by Reproducing 2,200 papers from ICML
98
August 13, 2026 
Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
16
August 12, 2026 
Thinking of ACE? We Can Do It with Fewer Tokens
30
August 11, 2026 
Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS
33
August 10, 2026 
Making Knowledge Distillation Cheap Enough to Run at Scale
35
August 10, 2026 
llmsvlmsmeta
Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
106
August 10, 2026 
llmsinference-providersbaseten
Baseten on Hugging Face Inference Providers 🔥
- +4
31
August 6, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
LiquidAI
• • 34Bedrock-RL: a deterministic Minecraft framework for training and benchmarking VLM agents
Michael-E
• • 14New imatrix dataset
bartowski
• • 12LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge
LiquidAI
• • 49ArmBench-ASR: A Benchmark for Armenian ASR
Metric-AI
• • 9We changed one line and the benchmark score moved 0.21 AUROC
FINAL-Bench
• • 9Sleeper Agents and How to Tame Them
tngtech
• • 26mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench
hotchpotch
• • 7Uncensor any LLM with abliteration
mlabonne
• • 900ECMWF's AI forecasting model is open source: now let's make it easy to run.
hugging-science
• • 17VLM Run Gateway: Run GLM-OCR, DeepSeek-OCR-2, dots.mocr with an OpenAI Compatible API
vlm-run
• • 5Code a simple RAG from scratch
ngxson
• • 381SraVaani: How Vision Helps Hearing
ARTPARK-IISc
• • 6KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 396Exploring NVIDIA Nemotron 3.5 Lightning: Making it see with little resources
tngtech
• • 16DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)
DedeProGames
• • 14Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed
basecompute
• • 3ColPali: Efficient Document Retrieval with Vision Language Models 👀
manu
• • 327From GRPO to DAPO and GSPO: What, Why, and How
NormalUhr
• • 140How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons
sherryxychen
• • 79