meta-llama / text-generation updated 1 year ago

Llama-3.2-1B-Instruct

Name: Llama-3.2-1B-Instruct
Author: meta-llama

Params

1.2 B

Context

—

Downloads 30d

10.4 M

Likes

1,553

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

Download history

daily snapshots · 10 days

10.4 M10.0 M

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	bf16	2.5 GB	3.4 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-3-2-1b-instruct
{
  "hf_id": "meta-llama/Llama-3.2-1B-Instruct",
  "params_b": 1.24,
  "context_length": null,
  "license": { "id": "llama3.2", "commercial": "conditional" },
  "downloads_30d": 10412058,
  "vram_estimates": [
    { "quant": "bf16", "gb": 3.4 }
  ],
  "updated_at": "2026-07-28T17:06:28Z"
}

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

Specifications

Architecture: LlamaForCausalLM
Parameters: 1.2 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-3.2-1B-Instruct-FP8-dynamic RedHatAI 1.5 M Derivative Llama-3.2-1B-Instruct-FP8 RedHatAI 799 K Derivative Llama-3.2-1B-Instruct unsloth 298 K Derivative Llama-3.2-1B-Instruct-Q8_0-GGUF hugging-quants 274 K Derivative Llama-3.2-1B-Instruct-GGUF bartowski 162 K

Compare with

Qwen3-0.6B 29.7 M Qwen2.5-1.5B-Instruct 14.0 M Qwen3-1.7B 7.8 M Qwen2.5-0.5B-Instruct 6.6 M gemma-3-1b-it 4.7 M Qwen2-1.5B-Instruct 3.2 M

Appears in

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