Qwen / image-text-to-text updated 3 months ago

Qwen3.5-35B-A3B-FP8

Name: Qwen3.5-35B-A3B-FP8
Author: Qwen

> [!Note] > This repository contains FP8-quantized 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. > > 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 mod...

Params

36.0 B

Context

—

Downloads 30d

924 K

Likes

153

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

Download history

daily snapshots · 7 days

924 K869 K

Jul 31Aug 2Aug 4Aug 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	37.5 GB	47.1 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: Qwen3_5MoeForConditionalGeneration
Parameters: 36.0 B
Tensor type: F8_E4M3
Licence: apache-2.0
First seen on the Hub: 2026-02-25
Base model: Qwen3.5-35B-A3B
Training datasets: undisclosed
Added to our catalog: 2026-07-31

Family

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

Base Qwen3.5-35B-A3B Qwen 2.6 M

Compare with

gemma-4-31B-it 11.9 M gemma-4-26B-A4B-it 11.7 M Qwen3.6-35B-A3B-FP8 8.9 M Qwen2.5-VL-3B-Instruct 8.2 M Qwen3.6-27B-FP8 7.8 M Qwen3.5-4B 6.7 M

Appears in

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