From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.smollmSubject: SmolLM3-3B-4bit Date: 2026-11-15Commit: d3a7e05Signed: 2DC28CC7B26A283B ✓ Text generation model with 3.1B parameters. Safetensors weights, 1.75 GB in all. Published by mlx-community under Apache-2.0.
3.1B params 1.75 GB SmolLM3-3B-4bit safetensors permissive Facts Params 3.1B Size 1.75 GB Formats safetensors Task text generation License Apache-2.0 permissive
fw
$ fw get mlx-community/SmolLM3-3B-4bit
# manifest sha256 b77bf182973d… · 1.75 GB · 10 files
$ fw verify ./SmolLM3-3B-4bit mlx-community/SmolLM3-3B-4bitHosted (signed) mlx-community/SmolLM3-3B-4bit Last check: 2026-11-15 04:55 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of SmolLM3-3B .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 1.75 GB
Weights 1.73 GB (safetensors)
Parameters 3.1B
Formats safetensors
Task text generation
License Apache-2.0 (permissive)
Files 10, each with a sha256
Publisher mlx-community
Added 2026-11-15
Section alt.freeweights.smollm Lineage
Original release from the publisher.
Base model: HuggingFaceTB/SmolLM3-3B
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 huggingface.co 2026-11-15 04:55 UTC passed
Model card From the publisher at commit
d3a7e05 . Shown as plain text with links; images open at the publisher.
This model mlx-community/SmolLM3-3B-4bit was converted to MLX format from HuggingFaceTB/SmolLM3-3B using mlx-lm version 0.25.3 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/SmolLM3-3B-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True) Files 10 files · 1.75 GB Weights 1.73 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 10 files with their sha256 File Size sha256 .gitattributes 1.57 KB 34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930 README.md 879 B d187c98aa68acb72167a95cb24fa75ac129f53bae235dddfbda60c7e065d1561 chat_template.jinja 5.50 KB 0dab472abbdc499c8d82acae3ad6e8404f672d2d50d9df582181daf062f66eb7 config.json 2.39 KB 6d0046fc9fc07c74601b25107b8ff96077dc9c63941492f2856743eabc2a3d99 generation_config.json 182 B 3458d62b3f9654f4bbe285223b0f4e5a1e67cae61c92bb6aeaadf04468bf9e01 model.safetensors 1.73 GB d501e6193d7eb84e10d3c377007d1fc4b4b2fa08799dd10fa4f6a75033334a70 model.safetensors.index.json 58.8 KB 64148ac05ad909f2fc69ec126ef9efe38545512a41914bdba17d1dc29437c19d special_tokens_map.json 289 B 12403efb970f069ba62ddf3b66166a27254be4a198166b61ad1ee604bd3a4515 tokenizer.json 17.2 MB 7b6a500b662a34eb3f0374db856ba4ad7de4c81040571d78dc0d357238930005 tokenizer_config.json 50.4 KB 59a64b39f05ee0acf7479bbccf99a44d9e481c1a4a494eb03838ae3c35eb29be
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents d3a7e0594d pinned now 2026-11-15 04:55 UTC 10 files · 1.75 GB
Use it fw
$ fw get mlx-community/SmolLM3-3B-4bit
# manifest sha256 b77bf182973d… · 1.75 GB · 10 files
$ fw verify ./SmolLM3-3B-4bit mlx-community/SmolLM3-3B-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/SmolLM3-3B-4bit.json --dir ./SmolLM3-3B-4bit
$ python3 fw.py verify ./SmolLM3-3B-4bit ./mlx-community__SmolLM3-3B-4bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/SmolLM3-3B-4bit --revision d3a7e0594d6642dbcfb7d149bed8b0bdf49f95ce --local-dir ./SmolLM3-3B-4bittransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("mlx-community/SmolLM3-3B-4bit", revision="d3a7e0594d6642dbcfb7d149bed8b0bdf49f95ce")
model = AutoModelForCausalLM.from_pretrained("mlx-community/SmolLM3-3B-4bit", revision="d3a7e0594d6642dbcfb7d149bed8b0bdf49f95ce", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/SmolLM3-3B-4bit --revision d3a7e0594d6642dbcfb7d149bed8b0bdf49f95ceLicense 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 d187c98aa68acb72167a95cb24fa75ac129f53bae235dddfbda60c7e065d1561 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: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.smollmSubject: SmolLM3-3B-4bit Date: 2026-11-15Commit: d3a7e05Signed: 2DC28CC7B26A283B ✓ Upstream mlx-community/SmolLM3-3B-4bit Pinned commit d3a7e0594d6642dbcfb7d149bed8b0bdf49f95ce Manifest SmolLM3-3B-4bit.json · .minisig Manifest sha256 b77bf182973dca20bd3e70fa604b188d1471aa0039d23478828acae28194aa8d Signature minisign, Ed25519, key 2DC28CC7B26A283B Created 2026-11-15 04:55 UTC Generator freeweights-manifest/0.1.0 Takedowns None. How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/SmolLM3-3B-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/SmolLM3-3B-4bit.json.minisig
$ minisign -Vm SmolLM3-3B-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 No model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/SmolLM3-3B-4bitOpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
135M params 272 MB 135M-lc-100k-rope-12B safetensors permissive Facts Params 135M Size 272 MB Formats safetensors Task text generation License Apache-2.0 permissive flip From: HuggingFaceTB <huggingface.co/HuggingFaceTB> Subject: 135M-lc-100k-rope-12B smollm 2.09 GB Biggie-SmoLlm-0.4B gguf permissive Facts Params not stated Size 2.09 GB Formats gguf Task text generation License Apache-2.0 permissive flip From: nisten <huggingface.co/nisten> Subject: Biggie-SmoLlm-0.4B smollm 4.29 GB Biggie-SmoLlm-0.4B-ONNX onnx permissive Facts Params not stated Size 4.29 GB Formats onnx Task text generation License unknown permissive flip From: <huggingface.co/onnx-community> Subject: Biggie-SmoLlm-0.4B-ONNX 1.8B params 1.04 GB SmolLM-1.7B-bnb-4bit safetensors permissive Facts Params 1.8B Size 1.04 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: SmolLM-1.7B-bnb-4bit 1.7B params 3.43 GB SmolLM-1.7B-Instruct safetensors permissive Facts Params 1.7B Size 3.43 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: SmolLM-1.7B-Instruct 138M params 115 MB SmolLM-135M-bnb-4bit safetensors permissive Facts Params 138M Size 115 MB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: SmolLM-135M-bnb-4bit
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.smollmSubject: 
onnx-community 
unsloth