RavenX MLX Models — Apple Silicon Inference Stack - a deadbydawn101 Collection

deadbydawn101 's Collections

RavenX MLX Models — Apple Silicon Inference Stack

RavenX MLX Models — Apple Silicon Inference Stack

updated 12 days ago

TurboQuant 4-bit mlx-lm models. TriAttention compatible. PR #1 merged MIT+NVIDIA.

deadbydawn101/gemma-4-E4B-mlx-4bit

Image-Text-to-Text • 2B • Updated 12 days ago • 3.76k • 4

Note RavenX 4-bit MLX — TurboQuant + TriAttention
deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit

Text Generation • Updated 6 days ago • 10.2k • 16

Note RavenX 4-bit MLX — TurboQuant + TriAttention
deadbydawn101/gemma-4-E2B-Heretic-Uncensored-mlx-4bit

Image-Text-to-Text • 1B • Updated 12 days ago • 6.31k • 8

Note RavenX 4-bit MLX — TurboQuant + TriAttention
deadbydawn101/gemma-4-21b-REAP-Tool-Calling-mlx-4bit

Image-Text-to-Text • 4B • Updated 12 days ago • 2.23k • 4

Note RavenX 4-bit MLX — TurboQuant + TriAttention
deadbydawn101/gemma-4-E4B-opus-reasoning-claude-code-lora

Text Generation • Updated 15 days ago • 1

Note RavenX 4-bit MLX — TurboQuant + TriAttention
Running

OpenClaw Agent Sandbox Demo

🖤

Run a sandboxed AI agent to complete your task

Note RavenX demo space
Running

Agents

Gemma 4 E4B — Agentic Tool Calling Demo

🖤

Chat with an AI that can calculate, fetch time, search web, run code

Note RavenX demo space