alt.freeweights.smollm / SmolVLM-500M-Instruct

From: HuggingFaceTB <huggingface.co/HuggingFaceTB>Newsgroups: alt.freeweights.smollmSubject:

SmolVLM-500M-Instruct

Date: 2026-11-15Commit: 753c175Signed: 2DC28CC7B26A283B ✓

Image text to text model with 507M parameters. Onnx and safetensors weights, 6.90 GB in all. Published by HuggingFaceTB under Apache-2.0.

507M params6.90GBSmolVLM-500M-Instructonnx safetensorspermissive

FactsParams507MSize6.90 GBFormatsonnx, safetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive

$ fw get HuggingFaceTB/SmolVLM-500M-Instruct
# manifest sha256 9f876103818a… · 6.90 GB · 38 files
$ fw verify ./SmolVLM-500M-Instruct HuggingFaceTB/SmolVLM-500M-Instruct

From sourceHosted (signed)HuggingFaceTB/SmolVLM-500M-InstructLast check: 2026-11-15 04:35 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

Run27 Fine-tune29 Convert15 Evaluate13 Scan13 Apps62

Runs with

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

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers

Transformers.js LMCache Xinference LMDeploy mistral.rs Mooncake

Show all 27

FlashInfer

AIBrix fastllm ExLlamaV3

ONNX Runtime GenAI

Transformers Ultralytics LocalAI tinygrad OpenVINO 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: 6.90 GB
Weights: 1.02 GB (safetensors)
Parameters: 507M
Formats: onnx, safetensors
Task: image text to text
License: Apache-2.0 (permissive)
Files: 38, each with a sha256
Publisher: HuggingFaceTB
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 04:35 UTC	passed

Model card

No model card stored here.No README was stored for this model. Read the publisher's page: https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct

Files

38 files · 6.90 GBWeights 1.02 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 38 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	9.92 KB	8465c1a46b0db5d5d0d0945df04032d1b405bb2fa12cdab3da1652bd75fca4b9
added_tokens.json	4.74 KB	74135b8664b56088c0006f1c8e848d79a8eba003411f72ebf1dc2ee96227be3a
chat_template.json	516 B	12462caec000542ca1bb73cd0ba25aaf320d90335fc46731fa6a8355ea34bd26
config.json	7.34 KB	daacbbca6af3c34e50466c72aed2df4553a08084f6a0551d4ae420a241cb66c6
generation_config.json	136 B	067a2a54e5f87162ecac6e0e911cc4665fc8f7f3324794ecbac0f76badb56636
merges.txt	466 KB	0b54e8aa4e53d5383e2e4bc635a56b43f9647f7b13832d5d9ecd8f82dac4f510
model.safetensors	1.02 GB	d05b567eeaf534e83d375551f068ed57b5f52d37c657197f644af5ef9db091a2
onnx/decoder_model_merged.onnx	1.45 GB	1d4dc5a8464c92cf151be233e23da809992e111f5596ba245fe1eca28e838b7b
onnx/decoder_model_merged_bnb4.onnx	207 MB	c3b311d0d34a7c067485ad9d440045c892a73885c7db52f13336b428d5c302e3
onnx/decoder_model_merged_fp16.onnx	725 MB	5425225b824ba82d9586ea7c719cde2c86c26fa5aaa5f43a1500a4fd40a5ee41
onnx/decoder_model_merged_int8.onnx	365 MB	36f53411b56c21868b0cf3d1fa0c1a7395ab88bcd1f7ae677bf91c54ab09cca0
onnx/decoder_model_merged_q4.onnx	229 MB	6d64c0fdce1c3515c40a08ff8e398bfbc0b2e961ae46d1b84b91e6a7b269b9d1
onnx/decoder_model_merged_q4f16.onnx	205 MB	7f828e9c1ae0290e766703677d1df2a8657ecadf24dfd55f5ff28ac23cf1cf41
onnx/decoder_model_merged_quantized.onnx	365 MB	69f48213b59637eee88e2b1af3c6bb23677fce77774a7237e8c1516c6b78ce47
onnx/decoder_model_merged_uint8.onnx	365 MB	69f48213b59637eee88e2b1af3c6bb23677fce77774a7237e8c1516c6b78ce47
onnx/embed_tokens.onnx	189 MB	6fe00a73de387cbe52cdb78f1b7c8bcda6bcb9974e40dc1b143315fc9f7e79af
onnx/embed_tokens_bnb4.onnx	189 MB	19f4fad7cb17c6dad11b4520d2abcba173fc91f755d71907d31d11a9e5761606
onnx/embed_tokens_fp16.onnx	94.6 MB	6b5f8cb6f78f90182bb60a3df22e9c47c93dc771d8d8172cce1f653f8da8a746
onnx/embed_tokens_int8.onnx	47.3 MB	f5f14887bf9b756d9fff2e412d474f0b5403e91f33b23460c9411f0ca54d945b
onnx/embed_tokens_q4.onnx	189 MB	19f4fad7cb17c6dad11b4520d2abcba173fc91f755d71907d31d11a9e5761606
onnx/embed_tokens_q4f16.onnx	94.6 MB	76c3b8232c463118190d1c711f2a7bff00a72f2077b9b19998f3a2c6344eb035
onnx/embed_tokens_quantized.onnx	47.3 MB	f5f14887bf9b756d9fff2e412d474f0b5403e91f33b23460c9411f0ca54d945b
onnx/embed_tokens_uint8.onnx	47.3 MB	f5f14887bf9b756d9fff2e412d474f0b5403e91f33b23460c9411f0ca54d945b
onnx/vision_encoder.onnx	393 MB	7ecd87031065252c5e3419f9a75db938a92cd5d55d2c22024d8815efd980104f
onnx/vision_encoder_bnb4.onnx	60.7 MB	e4af9028ddd3357b50a4d823987bb81bf2aca83eeba425bfc02aaa339eeca9f4
onnx/vision_encoder_fp16.onnx	197 MB	b2fca5aecb5fe29549ce0a1cc3091f64f7f33dafb5f5f215e2b774b5cf1eeec3
onnx/vision_encoder_int8.onnx	99.0 MB	50b814aa048a996bf5d5128a16c19046371a9a1aae24b930672f550af6c43646
onnx/vision_encoder_q4.onnx	66.7 MB	179812d5b1315edbe3e7164ea3d847c52723692e83ac9c770a5234962663fcad
onnx/vision_encoder_q4f16.onnx	57.7 MB	d5f3df9fd7113e564b1e167de20750572d25fd75c822365f496ff467bc9e7457
onnx/vision_encoder_quantized.onnx	99.0 MB	0612873758c96d759910a45dddbd150ea26d40cffb1ae49f391ea39dcbf50c09
onnx/vision_encoder_uint8.onnx	99.0 MB	0612873758c96d759910a45dddbd150ea26d40cffb1ae49f391ea39dcbf50c09
preprocessor_config.json	486 B	6cb6e36d6fcb88ca1502c4a26750715dc3e7dedddc9a8f17b27d8d167d1457e7
processor_config.json	68 B	e7bff42da73ae9eec9042ef20e066e11f1ee20f025358ff79131e3c0fb549b46
special_tokens_map.json	1.07 KB	aa0ff906077086dfa9734a7f97f68c825877a48f9468807be65504495cdeef09
tokenizer.json	3.55 MB	5ece781dc8d2b2f3e2f289ca0ae50b17cfc27dd27bfe7971bb8241e0b964331a
tokenizer_config.json	28.3 KB	8a68fb58021bc3df79d70f3d5fa79d2e709083872be1f6965cc9bcd12f3ba66a
vocab.json	801 KB	82b84012e3add4d01d12ba14442026e49b8cbbaead1f79ecf3d919784f82dc79

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

Upstream commit	Date	Contents
753c175260 pinned now	2026-11-15 04:35 UTC	38 files · 6.90 GB

Use it

$ fw get HuggingFaceTB/SmolVLM-500M-Instruct
# manifest sha256 9f876103818a… · 6.90 GB · 38 files
$ fw verify ./SmolVLM-500M-Instruct HuggingFaceTB/SmolVLM-500M-Instruct

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

$ python3 fw.py get https://freeweights.allternit.com/manifests/HuggingFaceTB/SmolVLM-500M-Instruct.json --dir ./SmolVLM-500M-Instruct
$ python3 fw.py verify ./SmolVLM-500M-Instruct ./HuggingFaceTB__SmolVLM-500M-Instruct.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download HuggingFaceTB/SmolVLM-500M-Instruct --revision 753c1752602b5e739af7a7fa6947a635051897a3 --local-dir ./SmolVLM-500M-Instruct

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForImageTextToText, AutoProcessor
processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-500M-Instruct", revision="753c1752602b5e739af7a7fa6947a635051897a3")
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM-500M-Instruct", revision="753c1752602b5e739af7a7fa6947a635051897a3", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve HuggingFaceTB/SmolVLM-500M-Instruct --revision 753c1752602b5e739af7a7fa6947a635051897a3

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: 8465c1a46b0db5d5d0d0945df04032d1b405bb2fa12cdab3da1652bd75fca4b9
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: HuggingFaceTB <huggingface.co/HuggingFaceTB>Newsgroups: alt.freeweights.smollmSubject: SmolVLM-500M-InstructDate: 2026-11-15Commit: 753c175Signed: 2DC28CC7B26A283B ✓

Upstream: HuggingFaceTB/SmolVLM-500M-Instruct
Pinned commit: 753c1752602b5e739af7a7fa6947a635051897a3
Manifest: SmolVLM-500M-Instruct.json · .minisig
Manifest sha256: 9f876103818ae3bb18be3d6503ba1ae06e44dace9b5764b8dbc40d65db1999dc
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:35 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/HuggingFaceTB/SmolVLM-500M-Instruct.json
$ curl -O https://freeweights.allternit.com/manifests/HuggingFaceTB/SmolVLM-500M-Instruct.json.minisig
$ minisign -Vm SmolVLM-500M-Instruct.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