RedHatAI / image-text-to-text updated 1 month ago

Qwen3.6-35B-A3B-NVFP4

Name: Qwen3.6-35B-A3B-NVFP4
Author: RedHatAI

This is a preliminary version (and subject to change) of NVFP4 quantized Qwen/Qwen3.6-35B-A3B model. The model has both weights and activations quantized to NVFP4 format with vllm-project/llm-compressor.

Params

34.7 B

Context

—

Downloads 30d

975 K

Likes

174

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

Download history

daily snapshots · 45 days

▲ 732 K in the last 30 days (42.9%)

1.9 M923 K

Aug 8Aug 23Sep 7Sep 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	u8	25.0 GB	33.2 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: 34.7 B
Tensor type: U8
Licence: apache-2.0
First seen on the Hub: 2026-04-17
Base model: Qwen3.6-35B-A3B
Training datasets: undisclosed
Added to our catalog: 2026-08-08

Family

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

Base Qwen3.6-35B-A3B Qwen 3.3 M

Compare with any image-text-to-text model

Popular comparisons

Qwen3-VL-8B-Instruct 19.7 M gemma-4-26B-A4B-it 10.0 M Qwen3.6-35B-A3B-FP8 9.5 M gemma-4-31B-it 9.0 M Qwen3.8-27B 7.3 M Qwen3.8-27B-FP8 6.9 M