Zubin

zubinb

·

AI & ML interests

None yet

Recent Activity

liked a model about 22 hours ago

ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF

liked a model 3 days ago

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF

liked a model 5 days ago

Qwen/Qwen3.8-27B-FP8

View all activity

Organizations

None yet

upvoted an article about 1 month ago

Article

Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

+2

pcuenq, merve, burtenshaw, ariG23498

•

Aug 10

• 111

upvoted 3 collections about 1 month ago

Nanbeige4.2-3B MLX

MLX conversions of Nanbeige4.2-3B (Looped Transformer): bf16 + 2-8 bit quants • 8 items • Updated 15 days ago • 2

Nanbeige4.2-3B quants (looped transformer)

FP8 default, LoopShield 4-bit loop-aware placement, NVFP4A16 speed pick. Gates + failure modes on each card. • 4 items • Updated Jul 23 • 1

heretic-models

Madness and heresy • 72 items • Updated 24 days ago • 18

upvoted an article about 1 month ago

Article

Deploy local agents everywhere with LFM2.5-2.6B

LiquidAI

•

Aug 4

• 97

upvoted a paper about 2 months ago

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Paper • 2607.27205 • Published Jul 29 • 141

upvoted 2 collections about 2 months ago

🎯 Liquid Nanos

Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 36 items • Updated Aug 3 • 136

VisionPsy

SOTA General-Purpose Multimodal Vision-Language Models for Edge deployment • 4 items • Updated Jul 30 • 10

upvoted 3 papers about 2 months ago

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Paper • 2010.05646 • Published Oct 12, 2020 • 2

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference

Paper • 2508.05835 • Published Aug 7, 2025 • 2

Triplet-Block Diffusion RWKV

Paper • 2605.25969 • Published May 25 • 27

upvoted 2 collections about 2 months ago

Web LLM Models

LiteRT models that can run on the Web • 17 items • Updated Jul 26 • 23

Tmax

Data and models associated with "Tmax: A simple recipe for terminal agents". paper: https://arxiv.org/abs/2606.23321 • 23 items • Updated Jun 23 • 20

upvoted 3 papers about 2 months ago

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

Paper • 2605.09635 • Published Jul 23 • 65

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published Jul 22 • 26

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

Paper • 2604.04514 • Published Apr 6 • 8

upvoted 3 collections about 2 months ago

MIRA World Model

Developed with General Intuition (https://www.generalintuition.com/), in collaboration with Epic Games. MIRA is a Multiplayer Interactive World Model. • 2 items • Updated Jul 15 • 1

Cactus Hybrid

A small, on-device model is fast and private, but sometimes wrong. We post-train models to know when they are wrong, run on any framework. • 4 items • Updated Jul 22 • 11

Selene-1-Mini

13 items • Updated Mar 2 • 10

upvoted a paper about 2 months ago

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

Paper • 2606.21627 • Published Jun 19 • 8