CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.glm / GLM-4.5-Air-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.glmSubject:

GLM-4.5-Air-8bit

Date: 2026-11-15Commit: ca44c76Signed: 2DC28CC7B26A283B ✓

Text generation model with 106.9B parameters. Safetensors weights, 114 GB in all. Published by mlx-community under MIT.

106.9B params114GBGLM-4.5-Air-8bitsafetensorspermissive
FactsParams106.9BSize114 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/GLM-4.5-Air-8bit
# manifest sha256 798e5f2baeef… · 114 GB · 32 files
$ fw verify ./GLM-4.5-Air-8bit mlx-community/GLM-4.5-Air-8bit
From sourceHosted (signed)mlx-community/GLM-4.5-Air-8bitLast check: 2026-11-15 05:16 UTC
Get help

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

Quantized of GLM-4.5-Air.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
114 GB
Weights
114 GB (safetensors)
Parameters
106.9B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
32, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.glm
Lineage

Original release from the publisher.

Base model: zai-org/GLM-4.5-Air

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 05:16 UTCpassed

Model card

From the publisher at commit ca44c76. Shown as plain text with links; images open at the publisher.

mlx-community/GLM-4.5-Air-8bit#

This model mlx-community/GLM-4.5-Air-8bit was converted to MLX format from zai-org/GLM-4.5-Air using mlx-lm version 0.26.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/GLM-4.5-Air-8bit")

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

32 files · 114 GBWeights 114 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 32 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md831 Bf49e5e466eeb98f29d58f3a6f1e33e12ce11704e31a125da282855d27d6ab7fd
chat_template.jinja3.24 KB44f815868bf02fa458dd2f741a338046f4bf45f398eb6d067766726b9d96cce3
config.json1.25 KBba19078ab0f467c55891629b9a89c2ef3a551b122b99a31133ac748e7cc7fc0c
generation_config.json155 B06ac18cb0e733da062bdb1d260247d52b1f6c4b10785fc733402f22a510da05d
model-00001-of-00023.safetensors5.09 GB2150efe052f2834bba66d756cc6cbc58287739a6c0696bb41b1d01f84839f4dc
model-00002-of-00023.safetensors4.98 GBe1e69161de7ebff64b0ec7843648c2c6ca0cd83dbc546859bc8cb8a98f2c5cf3
model-00003-of-00023.safetensors4.98 GBa7d74de0edf4bbeb0b425e6951f044c479978507ddbec1727435e98352c4ac02
model-00004-of-00023.safetensors4.98 GB77159d514bb650e20083bc79572857a79a118cc85258c85b3cf1baee9fe7fd59
model-00005-of-00023.safetensors4.98 GBe99b06d48c8948dcfab4e7b572d7eaf66a655844a782c3f07e514b8bdc14150e
model-00006-of-00023.safetensors4.98 GB82c3c4664bfa21c74e1e23bf83467e448a98f20a39d048ba38feea6856d38c7c
model-00007-of-00023.safetensors4.98 GB7bf6f85e9c3ffc0930f4ceabab2e0bed2a918976216d6a7cc4529173b2dc5221
model-00008-of-00023.safetensors4.98 GB4cd7a614ca8105ceac57ebc6d57c402661af63923b33e12df84e4bdaf15d2220
model-00009-of-00023.safetensors4.98 GB7e47e360df3ecd9aeda87f8a32588980fff11c99bc688043c11bfddc2a955b67
model-00010-of-00023.safetensors4.98 GB43216a0cc1b2bd88486759481887935b0f761e97cd06d8f458bb049876ddc3b3
model-00011-of-00023.safetensors4.98 GB736145a6599fc6306e3ed46d3eb7821ad3bd3b4a768a9456ddd2a2a4b18d1054
model-00012-of-00023.safetensors4.98 GB307494f0e0fb2a15ba67dfe3a437e074938a8e5508aa024ad58f94f25e6e0c2e
model-00013-of-00023.safetensors4.98 GB9e8e50998ba2f1954d4d340c0fe719a544c0349b60443bc1eaa9edd07bf3753d
model-00014-of-00023.safetensors4.98 GB43d11215f67f8b99c6b7082af52f8d1c20147efcb2b47dc65eb12dc31350cb92
model-00015-of-00023.safetensors4.98 GB3a6aaa9173c236866f3a76a2d2e1ec8ad95947c610d06f8af15a35a2cdc66565
model-00016-of-00023.safetensors4.98 GBb0b8d00f2ef23e5ddf329fdec11d45c3cd6cda5b7f74c25266e72cb4880fdee5
model-00017-of-00023.safetensors4.98 GBe23a8afc484f33941327064df40c0605028761c27b527240a95ccfb7c0e5c100
model-00018-of-00023.safetensors4.98 GBa0e31bfa1bc6c753c43327b2fb22ed5e14a2f243e50438fd23014517abf7bae9
model-00019-of-00023.safetensors4.98 GBce0e7337b33d89378b095cf6bc5043c46f786fa8bedf715efb5a401fc1da1777
model-00020-of-00023.safetensors4.98 GB09b07559e7bff638c3ef8794b177be914f4906335613f51cc8756fa238275a83
model-00021-of-00023.safetensors4.98 GB84339cc074a2e0c72c36ca5326dc70c37063c247ce28ae0e30fb8aa65c5a61f8
model-00022-of-00023.safetensors4.98 GB4487b8de74860ce977384526996c8b27c80d7034f8b6d72387d0166d62032692
model-00023-of-00023.safetensors3.95 GBe6bc60975cb7e5f5025d991bf78fe6ee805c51395fe5b0f57ab8aa186eae7303
model.safetensors.index.json155 KBf477cad00e001a1f334bf4ee507dde2215cd0a38de50b2f092e1e13935a9cee2
special_tokens_map.json802 B290511061f3c229783aaa9b2d63698fdcffcc068890ce2e014275ebc6df1221a
tokenizer.json20.0 MBbda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
tokenizer_config.json7.31 KB27d01309c0ae7b5edb6511daabfcbf772b60e21c65cbb74d059acc76796f7897
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
ca44c769a9 pinned now2026-11-15 05:16 UTC32 files · 114 GB

Use it

$ fw get mlx-community/GLM-4.5-Air-8bit
# manifest sha256 798e5f2baeef… · 114 GB · 32 files
$ fw verify ./GLM-4.5-Air-8bit mlx-community/GLM-4.5-Air-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/GLM-4.5-Air-8bit.json --dir ./GLM-4.5-Air-8bit $ python3 fw.py verify ./GLM-4.5-Air-8bit ./mlx-community__GLM-4.5-Air-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/GLM-4.5-Air-8bit --revision ca44c769a97034e91466f2a524b6ef2c28eb3c1f --local-dir ./GLM-4.5-Air-8bit
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/GLM-4.5-Air-8bit", revision="ca44c769a97034e91466f2a524b6ef2c28eb3c1f") model = AutoModelForCausalLM.from_pretrained("mlx-community/GLM-4.5-Air-8bit", revision="ca44c769a97034e91466f2a524b6ef2c28eb3c1f", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/GLM-4.5-Air-8bit --revision ca44c769a97034e91466f2a524b6ef2c28eb3c1f

License

Name
MIT License
Id
MIT
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
f49e5e466eeb98f29d58f3a6f1e33e12ce11704e31a125da282855d27d6ab7fd
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.glmSubject: GLM-4.5-Air-8bitDate: 2026-11-15Commit: ca44c76Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/GLM-4.5-Air-8bit
Pinned commit
ca44c769a97034e91466f2a524b6ef2c28eb3c1f
Manifest
GLM-4.5-Air-8bit.json · .minisig
Manifest sha256
798e5f2baeef2250eeb862a9430f63be0c355c6efc2519a4c882e1494f2b8a26
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:16 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/GLM-4.5-Air-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/GLM-4.5-Air-8bit.json.minisig $ minisign -Vm GLM-4.5-Air-8bit.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

zai-org/GLM-4.5-Air · 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/GLM-4.5-Air-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. GLM-4.5-Air-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/GLM-4.5-Air-8bit

Related models

All of alt.freeweights.glm →
From: bartowski <huggingface.co/bartowski>Subject: arcee-ai_GLM-4-32B-Base-32K-GGUF
From: ggml-org <huggingface.co/ggml-org>Subject: AutoGLM-Phone-9B-GGUF
From: zai-org <huggingface.co/zai-org>Subject: cogagent-chat-hf
From: zai-org <huggingface.co/zai-org>Subject: CogView3-Plus-3B
From: zai-org <huggingface.co/zai-org>Subject: cogvlm-base-490-hf
From: laion <huggingface.co/laion>Subject: dev_set_part1_10k_glm_4_7_traces_jupiter