meta-llama / text-generation updated 1 year ago

Llama-3.1-405B-FP8

Name: Llama-3.1-405B-FP8
Author: meta-llama

Params

405.9 B

Context

—

Downloads 30d

493 K

Likes

123

Commercial use: conditional · llama3.1 Gated — accept licence SAFETENSORS 8 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

493 K419 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	487.2 GB	597.3 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 · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/llama-3-1-405b-fp8
{
  "hf_id": "meta-llama/Llama-3.1-405B-FP8",
  "params_b": 405.87,
  "context_length": null,
  "license": { "id": "llama3.1", "commercial": "conditional" },
  "downloads_30d": 493412,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 597.3 }
  ],
  "updated_at": "2026-07-28T18:05:45Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: LlamaForCausalLM
Parameters: 405.9 B
Tensor type: F8_E4M3
Licence: llama3.1
First seen on the Hub: 2024-07-20
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

DeepSeek-R1 9.9 M gpt-oss-120b 4.2 M DeepSeek-V4-Flash 2.7 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M GLM-5.2-NVFP4 1.8 M

Appears in

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