nvidia / text-generation updated 1 year ago

Qwen3-8B-FP8

The NVIDIA Qwen3-8B FP8 model is the quantized version of Alibaba's Qwen3-8B model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Qwen3-8B FP8 model is quantized with TensorRT Model Optimizer.

Params
8.2 B
Context
40,960
Downloads 30d
240 K
Likes
6
Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 42 days
▲ 229 K in the last 30 days (48.9%)
469 K173 K
Aug 11Aug 25Sep 8Sep 21

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 9.4 GB 12.1 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 40K ctx 9.4 GB 17.0 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 · api/v1
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-8b-fp8-nvidia
{
  "hf_id": "nvidia/Qwen3-8B-FP8",
  "params_b": 8.19,
  "context_length": 40960,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 239712,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 12.1 }
  ],
  "updated_at": "2026-08-11T01:00:25Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen3ForCausalLM
Parameters
8.2 B
Tensor type
F8_E4M3
Context length
40,960
Vocabulary
151,936
Layers / heads
36 / 32
Licence
apache-2.0
First seen on the Hub
2025-09-09
Base model
Qwen3-8B
Training datasets
undisclosed
Added to our catalog
2026-08-11

Family

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

Compare with any text-generation model