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
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.
| File | Quant | Size | Est. VRAM | Verdict 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 -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"
}
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
Compare with any text-generation model