meta-llama / text-generation updated 1 year ago

Llama-3.1-70B-Instruct

Name: Llama-3.1-70B-Instruct
Author: meta-llama

Params

70.6 B

Context

—

Downloads 30d

203 K

Likes

977

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

Download history

daily snapshots · 56 days

▲ 531 K in the last 30 days (72.3%)

1.0 M203 K

Jul 28Aug 15Sep 3Sep 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	bf16	141.1 GB	166.3 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-3-1-70b-instruct
{
  "hf_id": "meta-llama/Llama-3.1-70B-Instruct",
  "params_b": 70.55,
  "context_length": null,
  "license": { "id": "llama3.1", "commercial": "conditional" },
  "downloads_30d": 203439,
  "vram_estimates": [
    { "quant": "bf16", "gb": 166.3 }
  ],
  "updated_at": "2026-07-28T18:03:42Z"
}

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

Specifications

Architecture: LlamaForCausalLM
Parameters: 70.6 B
Tensor type: BF16
Licence: llama3.1
First seen on the Hub: 2024-07-16
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-generation model

Popular comparisons

OTel-2.0-LLM-31B-IT 6.6 M Qwen-72B 4.2 M Gemma-4-31B-IT-NVFP4 1.6 M Qwen2.5-Coder-32B-Instruct-AWQ 1.5 M Qwen3-32B-AWQ 811 K DeepSeek-R1-Distill-Llama-70B 189 K