Modelpublic

musk12/apple-fastvlm-qwen2-q4-gguf

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes16downloads

Model Card

FastVLM Qwen2 (Q4KM, GGUF)

A Qwen2 GGUF model quantized in Q4KM format for CPU memory-efficient inference. This FastVLM LLM backbone is optimized for low-memory and low-latency CPU deployment.

Model file

—fastvlm_qwen2_q4km.gguf

Usage

Use this model with llama.cpp-compatible runtimes for fast CPU-based language generation in FastVLM.

bash

./llama-cli -m fastvlm_qwen2_q4km.gguf -p "Your prompt here"

Base models

Derived from:

—apple/FastVLM-0.5B
—Qwen/Qwen2-0.5B