Ilyas Moutawwakil's picture

Ilyas Moutawwakil

IlyasMoutawwakil

·

IlyasMoutawwakil

AI & ML interests

Optimization, LLMs, Hardware, Backends, ..

Recent Activity

updated a Space 8 days ago

vibe-check/vibecheck

updated a model 16 days ago

IlyasMoutawwakil/sonic-moe

published a model about 1 month ago

IlyasMoutawwakil/sonic-moe

View all activity

Organizations

liked a Space 4 months ago

Qwen3-TTS Demo

Generate custom speech from text, voice descriptions, or samples

liked 2 Spaces 5 months ago

KVPress Leaderboard

KVPress leaderboard: benchmark KV Cache compression methods

CircleCI Test Collection Helper Space

Query test results for a PR

liked a model about 1 year ago

cognition-ai/Kevin-32B

33B • Updated May 6, 2025 • 138 • 164

liked 2 Spaces over 1 year ago

The Ultra-Scale Playbook

The ultimate guide to training LLM on large GPU Clusters

Dataset Migrator

Migrate datasets from GitHub or Kaggle to Hugging Face Hub

liked 2 models over 1 year ago

Qwen/QwQ-32B-Preview

Text Generation • 33B • Updated Jan 12, 2025 • 13.1k • • 1.74k

stabilityai/stable-diffusion-3-medium-diffusers

Text-to-Image • Updated Jun 19, 2024 • 174k • • 448

liked a Space over 1 year ago

OpenVINO Benchmark

Benchmark models using PyTorch and OpenVINO

liked 5 Spaces almost 2 years ago

Model Memory Utility

Calculate GPU memory needed for training Hugging Face models

OpenVINO Export

Export a Hugging Face model to OpenVINO format

LlamaGen

Real-time Whisper WebGPU

Transcribe audio to text instantly using WebGPU

FineWeb: decanting the web for the finest text data at scale

Explore and download the FineWeb web‑scale text dataset

liked 2 Spaces about 2 years ago

Reward Bench Leaderboard

Explore and compare model scores on RewardBench benchmarks

Phi-3 WebGPU

A private and powerful AI that runs locally in your browser

liked 3 models about 2 years ago

huggyllama/llama-30b

Text Generation • 33B • Updated Apr 7, 2023 • 2.07k • 48

huggyllama/llama-65b

Text Generation • 65B • Updated Apr 7, 2023 • 1.45k • 77

meta-llama/Meta-Llama-3-8B

Text Generation • 8B • Updated Sep 27, 2024 • 2M • • 6.55k

liked a Space about 2 years ago

FastRAG Haystack Pipeline