SmolVLM Grows Smaller – Introducing the 256M & 500M Models!

SmolVLM - small yet mighty Vision Language Model

SmolLM - blazingly fast and remarkably powerful

Investing in Performance: Fine-tune small models with LLM insights - a CFM case study

When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants

arXiv:2609.14146v1 Announce Type: cross Abstract: Vision-language-action (VLA) deployment can reduce inference latency while changing closed-loop task behavior. We evaluate HuggingFaceVLA/smolvla_lib...

Finer is Better (with the Right Scaling)

arXiv:2605. 08565v2 Announce Type: replace Abstract: Microscaling is a critical technique for preserving the quality of Large Language Models (LLMs) quantized to ultra-low precision formats.

Accelerate your models with 🤗 Optimum Intel and OpenVINO

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

arXiv:2607. 22034v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting.

Zamba2-VL Technical Report

arXiv:2606. 00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with a small number of shared transformer blocks.

Tile-Level Activation Overlap for Efficient LLM Inference

arXiv:2607. 02521v1 Announce Type: cross Abstract: SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time.

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

arXiv:2607. 01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation.

Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs

Scale-QLoRA introduces a method for merging LoRA adapters into native 4‑bit microscaling language models without altering the quantized code plane. By training only the per‑block scale field and freezing the E2M1 code, the merged model remains code‑invariant and can be deployed as a single checkpoint. Experiments on four models and tasks show that Scale‑QLoRA achieves accuracy‑lossless merging comparable to merge‑aware QAT‑LoRA, while offering benefits such as exact rollback, code‑plane deduplication, and a 125× faster scale‑only task swap.

GGUF-Metadata Prediction of Single-Sequence llama.cpp Throughput Across Three Systems

The paper predicts single‑sequence llama.cpp throughput from GGUF metadata using roofline‑shaped predictors with quantization‑specific scale factors. Experiments on 318 measurements across 53 host‑file configurations on two Apple M4 Max systems and an NVIDIA RTX 5080 show that an active‑parameter decode model achieves significantly lower mean absolute percentage errors compared to models that use total parameters. The study also finds that low‑bit model ladders alter runtime ordering and that GGUF structure improves predictions, though fitted efficiencies vary across systems.