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

Qwen3.6-27B-FP8

Name: Qwen3.6-27B-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

27.8 B

Context

—

Downloads 30d

7.8 M

Likes

340

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

Download history

daily snapshots · 10 days

7.8 M7.2 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	30.9 GB	38.6 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: Qwen3_5ForConditionalGeneration
Parameters: 27.8 B
Tensor type: F8_E4M3
Licence: apache-2.0
First seen on the Hub: 2026-04-21
Base model: Qwen3.6-27B
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base Qwen3.6-27B Qwen 7.0 M

Compare with

Qwen3.5-9B 12.4 M gemma-4-31B-it 11.9 M gemma-4-26B-A4B-it 11.7 M Qwen3.6-35B-A3B-FP8 8.9 M Qwen3.6-27B 7.0 M Qwen3.6-35B-A3B 5.9 M

Appears in

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