alt.freeweights.qwen / Qwen3-4B-Instruct-2507-4bit-DWQ-2510

From:

mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-4B-Instruct-2507-4bit-DWQ-2510

Date: 2026-11-15Commit: c073725Signed: 2DC28CC7B26A283B ✓

Text generation model with 4B parameters. Safetensors weights, 2.28 GB in all. Published by mlx-community under Apache-2.0.

4B params

2.28GBQwen3-4B-Instruct-2507-4bit-DWQ-2510safetensorspermissive

FactsParams4BSize2.28 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510
# manifest sha256 cee1176ecd8f… · 2.28 GB · 13 files
$ fw verify ./Qwen3-4B-Instruct-2507-4bit-DWQ-2510 mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510

From sourceHosted (signed)mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510Last check: 2026-11-15 05:07 UTC

Run at home Get help

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

Quantized of Qwen3-4B-Instruct-2507.

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: 2.28 GB
Weights: 2.26 GB (safetensors)
Parameters: 4B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 13, each with a sha256
Publisher: mlx-community
Added: 2026-11-15
Section: alt.freeweights.qwen

Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-4B-Instruct-2507

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 05:07 UTC	passed

Model card

From the publisher at commit c073725. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510#

This model mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510 was converted to MLX format from Qwen/Qwen3-4B-Instruct-2507 using mlx-lm version 0.28.2.

Use with mlx#

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510")

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

13 files · 2.28 GBWeights 2.26 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 13 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	1.00 KB	f5ad5afbf2771a6f32dcef92b505345199ebf910fb1c312bcd36e60820b08335
added_tokens.json	707 B	c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja	2.63 KB	64f85b198065d0fba2a81f37e10ed68161ce2c19a754c7100e67e0ca2ee9c326
config.json	990 B	387b98441ee36d609cb2657646fb8ab7cedaecbff1c83422e4d4a61b4f49e8a3
generation_config.json	238 B	835fffe355c9438e7a25be099b3fccaa98350b83451f9fd2d99512e74f1ade48
merges.txt	1.67 MB	8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model.safetensors	2.26 GB	bf7129c6518c5743080e687855a6ae4a4fb307de5d6239a18527d270dd960f69
model.safetensors.index.json	64.0 KB	388d811b8b7c2608dd04cce1bcb04a8bf715d19b42790894e6d3427ff429a777
special_tokens_map.json	613 B	76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json	11.4 MB	aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json	5.41 KB	4b5f2f80f84faefe8420e1616671adb1dd3d7e632038d34b1f0e3a1363a51059
vocab.json	2.78 MB	ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

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

Upstream commit	Date	Contents
c073725c8a pinned now	2026-11-15 05:07 UTC	13 files · 2.28 GB

Use it

$ fw get mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510
# manifest sha256 cee1176ecd8f… · 2.28 GB · 13 files
$ fw verify ./Qwen3-4B-Instruct-2507-4bit-DWQ-2510 mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510

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

$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510.json --dir ./Qwen3-4B-Instruct-2507-4bit-DWQ-2510
$ python3 fw.py verify ./Qwen3-4B-Instruct-2507-4bit-DWQ-2510 ./mlx-community__Qwen3-4B-Instruct-2507-4bit-DWQ-2510.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510 --revision c073725c8ac051eabad9d64f4dcd3019d1072559 --local-dir ./Qwen3-4B-Instruct-2507-4bit-DWQ-2510

transformersLoad 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/Qwen3-4B-Instruct-2507-4bit-DWQ-2510", revision="c073725c8ac051eabad9d64f4dcd3019d1072559")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510", revision="c073725c8ac051eabad9d64f4dcd3019d1072559", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510 --revision c073725c8ac051eabad9d64f4dcd3019d1072559

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: f5ad5afbf2771a6f32dcef92b505345199ebf910fb1c312bcd36e60820b08335
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:

mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject: Qwen3-4B-Instruct-2507-4bit-DWQ-2510Date: 2026-11-15Commit: c073725Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510
Pinned commit: c073725c8ac051eabad9d64f4dcd3019d1072559
Manifest: Qwen3-4B-Instruct-2507-4bit-DWQ-2510.json · .minisig
Manifest sha256: cee1176ecd8f7d0ee8d820747d1a2a824fff8aaeb3051efb3e1a4102ed4724c9
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:07 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510.json.minisig
$ minisign -Vm Qwen3-4B-Instruct-2507-4bit-DWQ-2510.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

Qwen/Qwen3-4B-Instruct-2507 · 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 mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. Qwen3-4B-Instruct-2507-4bit-DWQ-2510.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510

Related models

All of alt.freeweights.qwen →

From:

BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen

From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1

From:

BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923

From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct

From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA

From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF

Qwen3-4B-Instruct-2507-4bit-DWQ-2510

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/Qwen3-4B-Instruct-2507-4bit-DWQ-2510#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models