Qwen / image-text-to-text updated 8 months ago

Qwen3-VL-8B-Instruct-FP8

Name: Qwen3-VL-8B-Instruct-FP8
Author: Qwen

> This repository contains an FP8 quantized version of the Qwen3-VL-8B-Instruct model. The quantization method is fine-grained fp8 quantization with block size of 128, and its performance metrics are nearly identical to those of the original BF16 model. Enjoy!

Params

8.8 B

Context

—

Downloads 30d

3.2 M

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

3.2 M2.8 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

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

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	10.6 GB	13.5 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: Qwen3VLForConditionalGeneration
Parameters: 8.8 B
Tensor type: F8_E4M3
Licence: apache-2.0
First seen on the Hub: 2025-10-11
Base model: Qwen3-VL-8B-Instruct
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base Qwen3-VL-8B-Instruct Qwen 4.9 M

Compare with

Qwen3.5-9B 12.4 M gemma-4-26B-A4B-it 11.7 M Qwen2.5-VL-7B-Instruct 9.3 M Qwen2.5-VL-3B-Instruct 8.2 M Qwen3.5-4B 6.7 M Qwen3-VL-8B-Instruct 4.9 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB