alt.freeweights.smollm / SmolLM2-1.7B-Instruct-Q8-mlx

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

SmolLM2-1.7B-Instruct-Q8-mlx

Date: 2026-11-15Commit: 2bb0b4cSigned: 2DC28CC7B26A283B ✓

Text generation model with 1.7B parameters. Safetensors weights, 1.82 GB in all. Published by HuggingFaceTB under Apache-2.0.

1.7B params1.82GBSmolLM2-1.7B-Instruct-Q8-mlxsafetensorspermissive

FactsParams1.7BSize1.82 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx
# manifest sha256 26efbea40a3a… · 1.82 GB · 10 files
$ fw verify ./SmolLM2-1.7B-Instruct-Q8-mlx HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx

From sourceHosted (signed)HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlxLast check: 2026-11-15 05:19 UTC

Run at home Get help

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

Quantized of SmolLM2-1.7B-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: 1.82 GB
Weights: 1.82 GB (safetensors)
Parameters: 1.7B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 10, each with a sha256
Publisher: HuggingFaceTB
Added: 2026-11-15
Section: alt.freeweights.smollm

Lineage

Original release from the publisher.

Base model: HuggingFaceTB/SmolLM2-1.7B-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 05:19 UTC	passed

Model card

From the publisher at commit 2bb0b4c. Shown as plain text with links; images open at the publisher.

HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx#

The Model HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx was converted to MLX format from HuggingFaceTB/SmolLM2-1.7B-Instruct using mlx-lm version 0.19.2.

Use with mlx#

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

10 files · 1.82 GBWeights 1.82 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 10 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	1.05 KB	d17f7362eea4d54e448d53a44df838042bc68953a2ef3b0ea786082079eae7d2
config.json	1.02 KB	727ae411d8d5657a3edebf6fb0b64c71fcf5ca65af01bc70434d89a82124b2a3
merges.txt	466 KB	0b54e8aa4e53d5383e2e4bc635a56b43f9647f7b13832d5d9ecd8f82dac4f510
model.safetensors	1.82 GB	2349d5384ac91889b42979e21e62fe5c7955cfe6083663552cf275ad6a678463
model.safetensors.index.json	39.2 KB	a93cf855a70c2821af876414dd0436b2fab2d152064c51f377004fd3ad331582
special_tokens_map.json	655 B	2b7379f3ae813529281a5c602bc5a11c1d4e0a99107aaa597fe936c1e813ca52
tokenizer.json	3.52 MB	7d27c493c729a66ecefc837280b05d948b1ed50d130eebdbf911b1b36cf38ed7
tokenizer_config.json	3.76 KB	a27f638bd2831f5c3dea654a75838930f2b11fbe550c4d4e1d5d7bd07157b2ee
vocab.json	801 KB	82b84012e3add4d01d12ba14442026e49b8cbbaead1f79ecf3d919784f82dc79

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

Upstream commit	Date	Contents
2bb0b4cebf pinned now	2026-11-15 05:19 UTC	10 files · 1.82 GB

Use it

$ fw get HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx
# manifest sha256 26efbea40a3a… · 1.82 GB · 10 files
$ fw verify ./SmolLM2-1.7B-Instruct-Q8-mlx HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx

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

$ python3 fw.py get https://freeweights.allternit.com/manifests/HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx.json --dir ./SmolLM2-1.7B-Instruct-Q8-mlx
$ python3 fw.py verify ./SmolLM2-1.7B-Instruct-Q8-mlx ./HuggingFaceTB__SmolLM2-1.7B-Instruct-Q8-mlx.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx --revision 2bb0b4cebf6f2e93b23779a44f8b93e185609046 --local-dir ./SmolLM2-1.7B-Instruct-Q8-mlx

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx", revision="2bb0b4cebf6f2e93b23779a44f8b93e185609046")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx", revision="2bb0b4cebf6f2e93b23779a44f8b93e185609046", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx --revision 2bb0b4cebf6f2e93b23779a44f8b93e185609046

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: d17f7362eea4d54e448d53a44df838042bc68953a2ef3b0ea786082079eae7d2
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: SmolLM2-1.7B-Instruct-Q8-mlxDate: 2026-11-15Commit: 2bb0b4cSigned: 2DC28CC7B26A283B ✓

Upstream: HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx
Pinned commit: 2bb0b4cebf6f2e93b23779a44f8b93e185609046
Manifest: SmolLM2-1.7B-Instruct-Q8-mlx.json · .minisig
Manifest sha256: 26efbea40a3aa4af0fd7d9faee64b3ee216fc8cb407a424262459214e7a58155
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:19 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx.json
$ curl -O https://freeweights.allternit.com/manifests/HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx.json.minisig
$ minisign -Vm SmolLM2-1.7B-Instruct-Q8-mlx.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/SmolLM2-1.7B-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 HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. SmolLM2-1.7B-Instruct-Q8-mlx.json. Provenance. Takedown history: none.

Source

huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx

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

SmolLM2-1.7B-Instruct-Q8-mlx

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models