CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Hermes-4-14B-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

Hermes-4-14B-4bit

Date: 2026-11-15Commit: 9aeab89Signed: 2DC28CC7B26A283B ✓

Text generation model with 14.8B parameters. Safetensors weights, 8.32 GB in all. Published by mlx-community under Apache-2.0.

14.8B params8.32GBHermes-4-14B-4bitsafetensorspermissive
FactsParams14.8BSize8.32 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Hermes-4-14B-4bit
# manifest sha256 f838a5dadcb5… · 8.32 GB · 14 files
$ fw verify ./Hermes-4-14B-4bit mlx-community/Hermes-4-14B-4bit
From sourceHosted (signed)mlx-community/Hermes-4-14B-4bitLast check: 2026-11-15 05:06 UTC
Run at homeGet help

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

Quantized of Hermes-4-14B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
8.32 GB
Weights
8.31 GB (safetensors)
Parameters
14.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
14, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: NousResearch/Hermes-4-14B

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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:06 UTCpassed

Model card

From the publisher at commit 9aeab89. Shown as plain text with links; images open at the publisher.

mlx-community/Hermes-4-14B-4bit#

This model mlx-community/Hermes-4-14B-4bit was converted to MLX format from NousResearch/Hermes-4-14B using mlx-lm version 0.27.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Hermes-4-14B-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

14 files · 8.32 GBWeights 8.31 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.37 KB1ec28208aa7b7bde9b905fdec7a35d06e841a4d10fc38c8a3bf36b6a530a79e2
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja3.89 KB6a0543ce2179f4b132ec309a37a6d2889cfb889fbf8ec343cfd26d4f6c2a710e
config.json2.03 KB6458ae6e3d183408c79f149f429a1cdb891c242d3feee1884df95927c5507b24
generation_config.json138 Bb328863942abeb295a003598c4f65b85a8e824ce7e67b20e260742dc30e45329
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00002.safetensors5.35 GBa6baa3d967d942e8cbcf994df6a37e09b0560d0e451c7cb6f5ef6ca87ac2a100
model-00002-of-00002.safetensors2.95 GBc011e14386bd3f8f57ff389e73670bff3477b7df81f70e56932901c6e16e6551
model.safetensors.index.json86.3 KB68203af51dbba47b391bb60d13058f22432355e0e3bd344a1f1461a458623614
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.40 KB443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
9aeab89dd2 pinned now2026-11-15 05:06 UTC14 files · 8.32 GB

Use it

$ fw get mlx-community/Hermes-4-14B-4bit
# manifest sha256 f838a5dadcb5… · 8.32 GB · 14 files
$ fw verify ./Hermes-4-14B-4bit mlx-community/Hermes-4-14B-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Hermes-4-14B-4bit.json --dir ./Hermes-4-14B-4bit $ python3 fw.py verify ./Hermes-4-14B-4bit ./mlx-community__Hermes-4-14B-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Hermes-4-14B-4bit --revision 9aeab89dd26169a6e813bf9073700301de4b669a --local-dir ./Hermes-4-14B-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("mlx-community/Hermes-4-14B-4bit", revision="9aeab89dd26169a6e813bf9073700301de4b669a") model = AutoModelForCausalLM.from_pretrained("mlx-community/Hermes-4-14B-4bit", revision="9aeab89dd26169a6e813bf9073700301de4b669a", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Hermes-4-14B-4bit --revision 9aeab89dd26169a6e813bf9073700301de4b669a
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
1ec28208aa7b7bde9b905fdec7a35d06e841a4d10fc38c8a3bf36b6a530a79e2
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.textSubject: Hermes-4-14B-4bitDate: 2026-11-15Commit: 9aeab89Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Hermes-4-14B-4bit
Pinned commit
9aeab89dd26169a6e813bf9073700301de4b669a
Manifest
Hermes-4-14B-4bit.json · .minisig
Manifest sha256
f838a5dadcb56a09b8b658da40397bd86e3a492111ef8cdafb385dcc244d2b5d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:06 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Hermes-4-14B-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Hermes-4-14B-4bit.json.minisig $ minisign -Vm Hermes-4-14B-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

NousResearch/Hermes-4-14B · 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/Hermes-4-14B-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Hermes-4-14B-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Hermes-4-14B-4bit

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B