CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.glm / GLM-4.5-Air-3bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.glmSubject:

GLM-4.5-Air-3bit

Date: 2026-11-15Commit: c4367dbSigned: 2DC28CC7B26A283B ✓

Text generation model with 106.9B parameters. Safetensors weights, 46.8 GB in all. Published by mlx-community under MIT.

106.9B params46.8GBGLM-4.5-Air-3bitsafetensorspermissive
FactsParams106.9BSize46.8 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/GLM-4.5-Air-3bit
# manifest sha256 e5be265624e9… · 46.8 GB · 19 files
$ fw verify ./GLM-4.5-Air-3bit mlx-community/GLM-4.5-Air-3bit
From sourceHosted (signed)mlx-community/GLM-4.5-Air-3bitLast check: 2026-11-15 05:16 UTC
Run at homeGet 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
46.8 GB
Weights
46.8 GB (safetensors)
Parameters
106.9B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
19, 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 c4367db. Shown as plain text with links; images open at the publisher.

mlx-community/GLM-4.5-Air-3bit#

This model mlx-community/GLM-4.5-Air-3bit was converted to MLX format from zai-org/GLM-4.5-Air using mlx-lm version 0.26.1.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/GLM-4.5-Air-3bit")

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

19 files · 46.8 GBWeights 46.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md831 Bb726371aed5f6cd7ca993af508ec022db4f5a3cde952b7a4dd78cae2c009128e
chat_template.jinja3.24 KB44f815868bf02fa458dd2f741a338046f4bf45f398eb6d067766726b9d96cce3
config.json1.25 KBf07c577044194f7e52f2e8ccaee53835b18e6659eb5eea797a6997411202fb05
generation_config.json155 B06ac18cb0e733da062bdb1d260247d52b1f6c4b10785fc733402f22a510da05d
model-00001-of-00010.safetensors5.17 GB98ddcbff420f5b342320e4c63c29009f1ea1cb9b4e1b71425d3a914ed2dafecb
model-00002-of-00010.safetensors5.13 GBe309b2e84e3c88332e0b10e5a272a18469656916f18c0d0ec13fdee2569c631c
model-00003-of-00010.safetensors5.13 GB8219c1998081e9bb14138a84afb4425797b530313e392ca6e47c2b7d0af7e589
model-00004-of-00010.safetensors5.13 GB7574a30cef46f9097b4984ef6cbef38f0f91e8afe752a5e436954d5d0d047210
model-00005-of-00010.safetensors5.13 GB9d7a235f48f27e055e44cf81f74ddd11ac727ca454aec5f791a428612074df17
model-00006-of-00010.safetensors5.13 GB76ffdc3c11defd1057364d22eeb03796dc8f44f64aa615fdbce32c21e665dbef
model-00007-of-00010.safetensors5.13 GB00bc7134642f412f6e25ec0eff35b118c047bf7faea389fce447a1cb6b6aa148
model-00008-of-00010.safetensors5.13 GBad867df6eb1dbf9e2d92eacd35234911af1143dfc5dac95c9a244f5b90053931
model-00009-of-00010.safetensors5.13 GB24221e9d82b8061d44ab574e3b48ec22340d9664fe77a3c9c9951a3587614ebb
model-00010-of-00010.safetensors603 MBcdfd9311b86f8a87132baa00ce8f8761f44e429704815e58a1b4d67d4a3e6003
model.safetensors.index.json155 KBcac39265af90f00c635b1c5c971329175b8db1e8cf015e1d0a84adfb602a1da1
special_tokens_map.json802 B290511061f3c229783aaa9b2d63698fdcffcc068890ce2e014275ebc6df1221a
tokenizer.json20.0 MBbda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
tokenizer_config.json7.31 KB14a3484d689dae8f6bf58c250617bfa95bd0c7404480cf3f3feb364f1f0394eb
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
c4367db469 pinned now2026-11-15 05:16 UTC19 files · 46.8 GB

Use it

$ fw get mlx-community/GLM-4.5-Air-3bit
# manifest sha256 e5be265624e9… · 46.8 GB · 19 files
$ fw verify ./GLM-4.5-Air-3bit mlx-community/GLM-4.5-Air-3bit
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-3bit.json --dir ./GLM-4.5-Air-3bit $ python3 fw.py verify ./GLM-4.5-Air-3bit ./mlx-community__GLM-4.5-Air-3bit.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-3bit --revision c4367db4696015335df032b8df2227814b277077 --local-dir ./GLM-4.5-Air-3bit
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-3bit", revision="c4367db4696015335df032b8df2227814b277077") model = AutoModelForCausalLM.from_pretrained("mlx-community/GLM-4.5-Air-3bit", revision="c4367db4696015335df032b8df2227814b277077", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/GLM-4.5-Air-3bit --revision c4367db4696015335df032b8df2227814b277077
Run at home

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
b726371aed5f6cd7ca993af508ec022db4f5a3cde952b7a4dd78cae2c009128e
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-3bitDate: 2026-11-15Commit: c4367dbSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/GLM-4.5-Air-3bit
Pinned commit
c4367db4696015335df032b8df2227814b277077
Manifest
GLM-4.5-Air-3bit.json · .minisig
Manifest sha256
e5be265624e9534b089a4acb39234226f1eb10ca628ffd738587aaed4df1cdf0
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-3bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/GLM-4.5-Air-3bit.json.minisig $ minisign -Vm GLM-4.5-Air-3bit.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-3bit
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-3bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/GLM-4.5-Air-3bit

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