HuggingFaceTB / text-generation updated 10 months ago

SmolLM2-360M-Instruct

Name: SmolLM2-360M-Instruct
Author: HuggingFaceTB

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device. More details in our paper: https://arxiv.org/abs/2502.02737

Params

360 M

Context

8,192

Downloads 30d

494 K

Likes

207

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

507 K494 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	bf16	0.7 GB	1.4 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/smollm2-360m-instruct
{
  "hf_id": "HuggingFaceTB/SmolLM2-360M-Instruct",
  "params_b": 0.36,
  "context_length": 8192,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 494122,
  "vram_estimates": [
    { "quant": "bf16", "gb": 1.4 }
  ],
  "updated_at": "2026-07-28T18:05:17Z"
}

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

Specifications

Architecture: LlamaForCausalLM
Parameters: 360 M
Tensor type: BF16
Context length: 8,192
Vocabulary: 49,152
Layers / heads: 32 / 15
Licence: apache-2.0
First seen on the Hub: 2024-10-31
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-0.6B 29.7 M gpt2 13.7 M Llama-3.2-1B-Instruct 10.4 M Qwen2.5-0.5B-Instruct 6.6 M gemma-3-1b-it 4.7 M Qwen2.5-0.5B 2.6 M

Appears in

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