meta-llama / text-generation updated 1 year ago

Llama-3.2-3B-Instruct

Name: Llama-3.2-3B-Instruct
Author: meta-llama

Params

3.2 B

Context

—

Downloads 30d

1.8 M

Likes

2,628

Commercial use: conditional · llama3.2 Gated — accept licence SAFETENSORS 8 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days

▲ 749 K in the last 30 days (68.8%)

1.9 M954 K

Jul 28Aug 15Sep 2Sep 20

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	6.4 GB	8.0 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/llama-3-2-3b-instruct
{
  "hf_id": "meta-llama/Llama-3.2-3B-Instruct",
  "params_b": 3.21,
  "context_length": null,
  "license": { "id": "llama3.2", "commercial": "conditional" },
  "downloads_30d": 1837816,
  "vram_estimates": [
    { "quant": "bf16", "gb": 8.0 }
  ],
  "updated_at": "2026-07-28T18:02:52Z"
}

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

Specifications

Architecture: LlamaForCausalLM
Parameters: 3.2 B
Tensor type: BF16
Licence: llama3.2
First seen on the Hub: 2024-09-18
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Derivative Llama-3.2-3B-Instruct-FP8-dynamic RedHatAI 260 K Derivative Llama-3.2-3B-Instruct-GGUF unsloth 230 K Derivative Llama-3.2-3B-Instruct unsloth 180 K Derivative Llama-3.2-3B-Instruct-GGUF bartowski 157 K

Compare with any text-generation model

Popular comparisons

Qwen3-8B 12.9 M Qwen2.5-7B-Instruct 9.7 M Qwen2.5-1.5B-Instruct 7.2 M Qwen3-4B 7.1 M Qwen2.5-3B-Instruct 5.1 M Qwen3-4B-Instruct-2507 4.0 M