Qwen3-32B-NVFP4
- Model Architecture: Qwen/Qwen3-32B - Input: Text - Output: Text - Model Optimizations: - Weight quantization: FP4 - Activation quantization: FP4 - Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. - Release Date: 6/25/2025 - Version: 1.0 - Model Developers: RedHatAI
Params
32.0 B
Context
40,960
Downloads 30d
144 K
Likes
9
Download history
daily snapshots · 51 days
▲ 263 K in the last 30 days (64.6%)
408 K144 K
Oct 12Oct 22Nov 1Nov 10
412 K144 K
Sep 21Oct 8Oct 25Nov 10
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 | u8 | 20.7 GB | 28.0 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 40K ctx | 20.7 GB | 47.2 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-nvfp4
{
"hf_id": "RedHatAI/Qwen3-32B-NVFP4",
"params_b": 32.00,
"context_length": 40960,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 144282,
"vram_estimates": [
{ "quant": "u8", "gb": 28.0 }
],
"updated_at": "2026-09-21T01:00:18Z"
}
Specifications
- Architecture
- Qwen3ForCausalLM
- Parameters
- 32.0 B
- Tensor type
- U8
- Context length
- 40,960
- Vocabulary
- 151,936
- Layers / heads
- 64 / 64
- Licence
- apache-2.0
- First seen on the Hub
- 2025-06-27
- Base model
- Qwen3-32B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-21
Compare with any text-generation model