raxcore-dev / image-text-to-text updated 2 months ago

Rax-4.5

> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. > > In light of its parameter scale, the intended use cases are prototyping, task-specific fine-tuning, and other research or development purposes.

Params
2.3 B
Context
Downloads 30d
846 K
Likes
5
Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 21 days
1.1 M846 K
Sep 1Sep 8Sep 15Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 4.5 GB 5.8 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
Qwen3_5ForConditionalGeneration
Parameters
2.3 B
Tensor type
BF16
Licence
apache-2.0
First seen on the Hub
2025-11-27
Base model
Rax-4.5
Training datasets
undisclosed
Added to our catalog
2026-09-01

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any image-text-to-text model