MLX Quantisations for Qwen 3.8 2B
🏗️ Building on HF
Siddh Jagani
SiddhJagani
AI & ML interests
Building local AI systems, LLM tools, RAG infrastructure, and MLX model deployments.
Recent Activity
updated a Space 6 days ago
SiddhJagani/Stats published a Space 6 days ago
SiddhJagani/Stats updated a model 6 days ago
SiddhJagani/Qwen3.8-4B-mlx-2BitOrganizations
spaces 19
pinned
Sleeping
Ultimate AI HUB
⚡
All Models for Free!
Running
Huggingface User Stats
💻
fetch hf user stats
Running
Vlm
🚀
Local Mind VLM is a Vision supported AI
Running
Local Mind
🏆
Local Mind is a Browser Based AI model
Sleeping
Agents
LuxTTS
🚀
Space for LuxTTS: a 150x realtime voice cloning TTS model
Sleeping
Agents
Qwen3-TTS Demo
🎙
Generate speech from text using design, clone, or preset voices
models 42
SiddhJagani/Qwen3.8-4B-mlx-2Bit
Text Generation • 0.4B • Updated • 520
SiddhJagani/Qwen3.8-4B-mlx-3Bit
Text Generation • 0.5B • Updated • 390
SiddhJagani/Qwen3.8-4B-mlx-4Bit
Text Generation • 0.7B • Updated • 491
SiddhJagani/Qwen3.8-4B-mlx-5Bit
Text Generation • 0.8B • Updated • 304
SiddhJagani/Qwen3.8-4B-mlx-6Bit
Text Generation • 0.9B • Updated • 338
SiddhJagani/Qwen3.8-4B-mlx-8Bit
Text Generation • 1B • Updated • 430
SiddhJagani/Qwen3.8-4B-mlx-fp16
Text Generation • 4B • Updated • 606
SiddhJagani/Qwen3.8-2B-mlx-2Bit
Text Generation • 0.2B • Updated • 327
SiddhJagani/Qwen3.8-2B-mlx-3Bit
Text Generation • 0.2B • Updated • 308
SiddhJagani/Qwen3.8-2B-mlx-4Bit
Text Generation • 0.3B • Updated • 357
datasets 0
None public yet