Qwen / text-generation updated 1 year ago

Qwen3-32B-FP8

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:

Params
32.8 B
Context
40,960
Downloads 30d
205 K
Likes
85
Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (4 recorded)
205 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f8_e4m3 34.3 GB 43.2 GB ❌ Won’t fit
model.safetensors (bf16, full) bf16 + 40K ctx 34.3 GB 62.8 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/qwen3-32b-fp8
{
  "hf_id": "Qwen/Qwen3-32B-FP8",
  "params_b": 32.76,
  "context_length": 40960,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 205398,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 43.2 }
  ],
  "updated_at": "2026-09-17T01:00:41Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen3ForCausalLM
Parameters
32.8 B
Tensor type
F8_E4M3
Context length
40,960
Vocabulary
151,936
Layers / heads
64 / 64
Licence
apache-2.0
First seen on the Hub
2025-04-28
Base model
Qwen3-32B
Training datasets
undisclosed
Added to our catalog
2026-09-17

Family

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

Compare with any text-generation model