Qwen / text-generation updated 1 year ago

Qwen3-8B-FP8

Name: Qwen3-8B-FP8
Author: Qwen

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

8.2 B

Context

40,960

Downloads 30d

876 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

876 K845 K

Jul 28Jul 31Aug 3Aug 6

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	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
{
  "hf_id": "Qwen/Qwen3-8B-FP8",
  "params_b": 8.19,
  "context_length": 40960,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 876416,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 12.1 }
  ],
  "updated_at": "2026-07-28T18:04:00Z"
}

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: 2025-04-28
Base model: Qwen3-8B
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base Qwen3-8B Qwen 16.3 M

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB