alt.freeweights.smollm / SmolLM2-360M-Instruct-bnb-4bit

From:

unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.smollmSubject:

SmolLM2-360M-Instruct-bnb-4bit

Date: 2026-11-15Commit: f468cacSigned: 2DC28CC7B26A283B ✓

Text generation model with 372M parameters. Safetensors weights, 262 MB in all. Published by unsloth under Apache-2.0.

372M params

262MBSmolLM2-360M-Instruct-bnb-4bitsafetensorspermissive

FactsParams372MSize262 MBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get unsloth/SmolLM2-360M-Instruct-bnb-4bit
# manifest sha256 ec5fb215a569… · 262 MB · 11 files
$ fw verify ./SmolLM2-360M-Instruct-bnb-4bit unsloth/SmolLM2-360M-Instruct-bnb-4bit

From sourceHosted (signed)unsloth/SmolLM2-360M-Instruct-bnb-4bitLast check: 2026-11-15 05:11 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of SmolLM2-360M-Instruct.

Works with

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 262 MB
Weights: 257 MB (safetensors)
Parameters: 372M
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 11, each with a sha256
Publisher: unsloth
Added: 2026-11-15
Section: alt.freeweights.smollm

Lineage

Original release from the publisher.

Base model: HuggingFaceTB/SmolLM2-360M-Instruct

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:11 UTC	passed

Model card

From the publisher at commit f468cac. Shown as plain text with links; images open at the publisher.

Finetune SmolLM2, Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!#

We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing

https://discord.gg/unsloth https://github.com/unslothai/unsloth

unsloth/SmolLM2-360M-Instruct 4bit bitsandbytes pre-quantized#

For more details on the model, please go to Hugging Face's original model card

✨ Finetune for Free#

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Llama-3.2 (3B)	▶️ Start on Colab	2.4x faster	58% less
Llama-3.2 (11B vision)	▶️ Start on Colab	2.4x faster	58% less
Llama-3.1 (8B)	▶️ Start on Colab	2.4x faster	58% less
Phi-3.5 (mini)	▶️ Start on Colab	2x faster	50% less
Gemma 2 (9B)	▶️ Start on Colab	2.4x faster	58% less
Mistral (7B)	▶️ Start on Colab	2.2x faster	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
\* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

Special Thanks#

A huge thank you to the Hugging Face team for creating and releasing these models.

Model Summary#

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.

The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using UltraFeedback.

The instruct model additionally supports tasks such as text rewriting, summarization and function calling thanks to datasets developed by Argilla such as Synth-APIGen-v0.1.

SmolLM2#

Image: image/png

Files

11 files · 262 MBWeights 257 MB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 11 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	4.59 KB	9b1f765e8d89a64172e864ea83dc64fb7cec01dd4f054b472f28bfd7b5438258
added_tokens.json	29 B	5a7038c26cb1d019b0258d86889308341cf8c0166978b05f5996be953bb69c9e
config.json	1.41 KB	eae539430c74780a97089bc31a207f4ee896225ee3a6ffde66f848e59e3f4302
generation_config.json	158 B	afb4d81568aa62eee418471ca6973ce906e0d21c1737aa3a6a4c697e00872e8d
merges.txt	466 KB	0b54e8aa4e53d5383e2e4bc635a56b43f9647f7b13832d5d9ecd8f82dac4f510
model.safetensors	257 MB	8df5bf4ddc613e993179101581d0c3e3bd584fda4efa763a9aeed58c2db0f6b4
special_tokens_map.json	423 B	8d39b597d486de3dd50200e067b418cb42ed5fd9b9fd0b4cfd8871eae9c65e1c
tokenizer.json	3.52 MB	66bfc9a0d05ad54eef8e1f906d77fd37663e8a51eb1c56b44d2e4227448f91fb
tokenizer_config.json	3.96 KB	bf4e0fd676862c396f9c6317c11fe3b395dc1f8fd5e6b48265d4a8d39e500588
vocab.json	801 KB	82b84012e3add4d01d12ba14442026e49b8cbbaead1f79ecf3d919784f82dc79

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
f468cac190 pinned now	2026-11-15 05:11 UTC	11 files · 262 MB

Use it

$ fw get unsloth/SmolLM2-360M-Instruct-bnb-4bit
# manifest sha256 ec5fb215a569… · 262 MB · 11 files
$ fw verify ./SmolLM2-360M-Instruct-bnb-4bit unsloth/SmolLM2-360M-Instruct-bnb-4bit

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/SmolLM2-360M-Instruct-bnb-4bit.json --dir ./SmolLM2-360M-Instruct-bnb-4bit
$ python3 fw.py verify ./SmolLM2-360M-Instruct-bnb-4bit ./unsloth__SmolLM2-360M-Instruct-bnb-4bit.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/SmolLM2-360M-Instruct-bnb-4bit --revision f468cac190838daa8e8e257f43bc508786ffbfe0 --local-dir ./SmolLM2-360M-Instruct-bnb-4bit

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("unsloth/SmolLM2-360M-Instruct-bnb-4bit", revision="f468cac190838daa8e8e257f43bc508786ffbfe0")
model = AutoModelForCausalLM.from_pretrained("unsloth/SmolLM2-360M-Instruct-bnb-4bit", revision="f468cac190838daa8e8e257f43bc508786ffbfe0", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve unsloth/SmolLM2-360M-Instruct-bnb-4bit --revision f468cac190838daa8e8e257f43bc508786ffbfe0

Run at home

License

Name: Apache License 2.0
Id: Apache-2.0
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: License as declared by the publisher. No person read it. 2026-11-15
Text in: README.md
Text sha256: 9b1f765e8d89a64172e864ea83dc64fb7cec01dd4f054b472f28bfd7b5438258
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From:

unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.smollmSubject: SmolLM2-360M-Instruct-bnb-4bitDate: 2026-11-15Commit: f468cacSigned: 2DC28CC7B26A283B ✓

Upstream: unsloth/SmolLM2-360M-Instruct-bnb-4bit
Pinned commit: f468cac190838daa8e8e257f43bc508786ffbfe0
Manifest: SmolLM2-360M-Instruct-bnb-4bit.json · .minisig
Manifest sha256: ec5fb215a569c1dba8fd901ede26b8a0a08d82b66eeb2eff954b2d74b4c8d56e
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:11 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/SmolLM2-360M-Instruct-bnb-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/unsloth/SmolLM2-360M-Instruct-bnb-4bit.json.minisig
$ minisign -Vm SmolLM2-360M-Instruct-bnb-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

HuggingFaceTB/SmolLM2-360M-Instruct · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/SmolLM2-360M-Instruct-bnb-4bit

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. SmolLM2-360M-Instruct-bnb-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/unsloth/SmolLM2-360M-Instruct-bnb-4bit

Related models

All of alt.freeweights.smollm →

From: HuggingFaceTB <huggingface.co/HuggingFaceTB>Subject: 135M-lc-100k-rope-12B

From: nisten <huggingface.co/nisten>Subject: Biggie-SmoLlm-0.4B

From:

onnx-community <huggingface.co/onnx-community>Subject: Biggie-SmoLlm-0.4B-ONNX

From:

unsloth <huggingface.co/unsloth>Subject: SmolLM-1.7B-bnb-4bit

From:

unsloth <huggingface.co/unsloth>Subject: SmolLM-1.7B-Instruct

From:

unsloth <huggingface.co/unsloth>Subject: SmolLM-135M-bnb-4bit

SmolLM2-360M-Instruct-bnb-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

Finetune SmolLM2, Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!#

unsloth/SmolLM2-360M-Instruct 4bit bitsandbytes pre-quantized#

✨ Finetune for Free#

Special Thanks#

Model Summary#

SmolLM2#

Files

Use it

License

Provenance

How to verify

Model tree

Related models