Qwen3-VL-30B-A3B-Instruct-FP8
> This repository contains an FP8 quantized version of the Qwen3-VL-30B-A3B-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
31.1 B
Context
—
Downloads 30d
801 K
Likes
115
Download history
daily snapshots · 37 days
▲ 44 K in the last 30 days (5.2%)
881 K801 K
Aug 23Sep 2Sep 12Sep 21
881 K801 K
Aug 16Aug 28Sep 9Sep 21
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 | 32.3 GB | 40.6 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen3VLMoeForConditionalGeneration
- Parameters
- 31.1 B
- Tensor type
- F8_E4M3
- Licence
- apache-2.0
- First seen on the Hub
- 2025-10-01
- Base model
- Qwen3-VL-30B-A3B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-16
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any image-text-to-text model