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

Qwen3.5-122B-A10B-FP8

Name: Qwen3.5-122B-A10B-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

125.1 B

Context

—

Downloads 30d

1.3 M

Likes

112

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

Download history

daily snapshots · 10 days

1.3 M1.2 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	127.2 GB	159.1 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: 125.1 B
Tensor type: F8_E4M3
Licence: apache-2.0
First seen on the Hub: 2026-02-25
Base model: Qwen3.5-122B-A10B
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base Qwen3.5-122B-A10B Qwen 2.2 M

Compare with

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 Qwen3-VL-4B-Instruct 4.0 M GLM-OCR 3.8 M

Appears in

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