Qwen3-14B-NVFP4
The NVIDIA Qwen3-14B FP4 model is the quantized version of Alibaba's Qwen3-14B model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Qwen3-14B FP4 model is quantized with TensorRT Model Optimizer.
Params
8.2 B
Context
40,960
Downloads 30d
713 K
Likes
17
Download history
daily snapshots · 14 days713 K213 K
Sep 8Sep 12Sep 17Sep 21
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 | 10.5 GB | 13.3 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 40K ctx | 10.5 GB | 18.2 GB | ✅ Runs comfortably |
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/qwen3-14b-nvfp4
{
"hf_id": "nvidia/Qwen3-14B-NVFP4",
"params_b": 8.16,
"context_length": 40960,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 713073,
"vram_estimates": [
{ "quant": "u8", "gb": 13.3 }
],
"updated_at": "2026-09-08T01:00:26Z"
}
Specifications
- Architecture
- Qwen3ForCausalLM
- Parameters
- 8.2 B
- Tensor type
- U8
- Context length
- 40,960
- Vocabulary
- 151,936
- Layers / heads
- 40 / 40
- Licence
- apache-2.0
- First seen on the Hub
- 2025-09-09
- Base model
- Qwen3-14B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-08
Compare with any text-generation model