Qwen / text-generation updated 10 months ago

Qwen3-Next-80B-A3B-Instruct-FP8

Name: Qwen3-Next-80B-A3B-Instruct-FP8
Author: Qwen

Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. We call this next-generation foundation models Qwen3-Next.

Params

81.3 B

Context

262,144

Downloads 30d

339 K

Likes

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

Download history

daily snapshots · 10 days

339 K331 K

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	82.1 GB	103.0 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	82.1 GB	481.1 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-next-80b-a3b-instruct-fp8
{
  "hf_id": "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8",
  "params_b": 81.33,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 339404,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 103.0 }
  ],
  "updated_at": "2026-07-28T18:06:17Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen3NextForCausalLM
Parameters: 81.3 B
Tensor type: F8_E4M3
Context length: 262,144
Vocabulary: 151,936
Layers / heads: 48 / 16
Licence: apache-2.0
First seen on the Hub: 2025-09-22
Base model: Qwen3-Next-80B-A3B-Instruct
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base Qwen3-Next-80B-A3B-Instruct Qwen 287 K

Compare with

gpt-oss-20b 8.6 M Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M gpt-oss-120b 4.2 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M Qwen3-Coder-Next-FP8 2.2 M

Appears in

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