CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.glm / GLM-4.6-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.glmSubject:

GLM-4.6-4bit

Date: 2026-11-15Commit: dfcf4c5Signed: 2DC28CC7B26A283B ✓

Text generation model with 352.8B parameters. Safetensors weights, 199 GB in all. Published by mlx-community under MIT.

352.8B params199GBGLM-4.6-4bitsafetensorspermissive
FactsParams352.8BSize199 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/GLM-4.6-4bit
# manifest sha256 f5ea96b33b71… · 199 GB · 48 files
$ fw verify ./GLM-4.6-4bit mlx-community/GLM-4.6-4bit
From sourceHosted (signed)mlx-community/GLM-4.6-4bitLast check: 2026-11-15 05:15 UTC
Get help

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

Quantized of GLM-4.6.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
199 GB
Weights
199 GB (safetensors)
Parameters
352.8B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
48, 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-4.6

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 05:15 UTCpassed

Model card

From the publisher at commit dfcf4c5. Shown as plain text with links; images open at the publisher.

mlx-community/GLM-4.6-4bit#

This model mlx-community/GLM-4.6-4bit was converted to MLX format from zai-org/GLM-4.6 using mlx-lm version 0.28.1.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/GLM-4.6-4bit")

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

48 files · 199 GBWeights 199 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 48 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md803 B2a1bfe79e14feb6a9c4ea1889af2a6a27caada2a5aaf3cb7f2ca988100498737
chat_template.jinja3.24 KB44f815868bf02fa458dd2f741a338046f4bf45f398eb6d067766726b9d96cce3
config.json1.30 KB7f79bf5b0a4f789d9f5434df521b2d3a572b87d5191cf69eba16f4b227f402f0
generation_config.json177 B71a6281557b989ff592e7a13fd170b8ab1e5700bac2313df6a64ee1f9286b3cf
model-00001-of-00039.safetensors5.36 GB6cdd51653b7504ff93ba82d11c96797592aa8ea9836318fd1f611f273a751bf7
model-00002-of-00039.safetensors5.27 GB096d28815e24dcc63fb682dbd272c8798c0c9993c5e811abdadf54e302430297
model-00003-of-00039.safetensors5.14 GB61ae0dd3f23e0849f21a0e1d6856e3e84d64f7ba40967c6bc2e278eb31701de5
model-00004-of-00039.safetensors5.23 GB1cfc501b74a796556e8417210dd3f2246504c3caac6c402839495049627605c3
model-00005-of-00039.safetensors5.14 GBe8a5f09e1b679a93ccc8e2341250a1947c6b5d4595c6f2773d6416421b3143db
model-00006-of-00039.safetensors5.14 GBc2360a70c72667e515ad5f216f5e3e3723188d822d73a1c487a7d46aeb2b2c3c
model-00007-of-00039.safetensors5.23 GB5e29748e7ad37b9f8f8b292487cd9271432aee1cd7f86587b6872f6f3994245c
model-00008-of-00039.safetensors5.14 GB18cfb96f71cf6f34817b1fa8be728b383032be5fa7609b5782a7fe7d5ff788dc
model-00009-of-00039.safetensors5.14 GBdcfc58e484f92a1b43f549ab38998c7ea62316c1d3702e1fc5113d2bee23955e
model-00010-of-00039.safetensors5.23 GB96d77981a4da67403b3bc497c100617898855dc6e5605e6921193b1a69a90892
model-00011-of-00039.safetensors5.14 GB2bb0ddb06ca2870d3aba9fc359696c138a302aa0ab8bf25bc58f6e073ee01a28
model-00012-of-00039.safetensors5.14 GB5aad56fefbdf1f0066ea762bf8ead25f6a7c17abbc20d38a403208321b930591
model-00013-of-00039.safetensors5.23 GB98b884730db3b5518d9b4c1ab49c5c41e02f3381ac71f4464de60be86d9c95f1
model-00014-of-00039.safetensors5.14 GB91dd7211d4a3d7bb7a40bf4aaa35cef22107192ce4e72b9c9cf67f1810d5d6b6
model-00015-of-00039.safetensors5.14 GB1dcfa07d7d71dde29b3d0cdacf14377307526e6b07a783c58c0030d498f4e927
model-00016-of-00039.safetensors5.23 GBdfc708333c62693747001d9f96d7f4ff05e7f32f015d130aa21720efad02e96e
model-00017-of-00039.safetensors5.14 GB3f7c89dc4302d9a9d6a139d87e04fa3bb45e0d335e3f5de62543f0eb19aff998
model-00018-of-00039.safetensors5.14 GBffaedcc6ef9acbb7cbbd5df0ccd094bef12b735ec512201aa09d77db053c9143
model-00019-of-00039.safetensors5.23 GB7057e2193d6a9e8b3bacf4739c77f24a9a3563a8265ca71e07b7cbd245be6799
model-00020-of-00039.safetensors5.14 GBd5a7772e361c6e1d6d653213e3435a04ac22329c15eb09dd6f904e66964ede62
model-00021-of-00039.safetensors5.14 GBf858947f38ae6483cfb970e9475571b156762ab33d27efcd0ccbed8071eff742
model-00022-of-00039.safetensors5.23 GB7f3b949cd95904b61f10982591c656c382d51dc4fe4adf6c11d2720695efe578
model-00023-of-00039.safetensors5.14 GB2431b003bfcd2a1408a1fdadd50681bc16e4adce59239751b7a518a5f4507539
model-00024-of-00039.safetensors5.14 GB82fa1cd36722da4a71cf9a524be44668d56af1f23f8b2205fee3a83a9c66f70c
model-00025-of-00039.safetensors5.23 GB4d251098ff05d7f26ece0d029f226595d531296e0380661a9e368637fee6a5f6
model-00026-of-00039.safetensors5.14 GBc73abdb5416346653e4ba32fb7a73004f9dfd330faaed82bbefb2c8645bc2892
model-00027-of-00039.safetensors5.14 GB92b8ef0d0843c0a3a4cba8342bdd99f11b4b1529850ac3e794124640eb8415e7
model-00028-of-00039.safetensors5.23 GB908ff032b83752799c8dc21ade94a83634e4efb999163a74927edd813df0e539
model-00029-of-00039.safetensors5.14 GBe33983608e38e3ac59fa7847378d833031db6f1ae58052a863b4c68035f99fb6
model-00030-of-00039.safetensors5.14 GB4d89251ad4d65158d84e3f2a3de070e1a41e99d2016b585e5f89e45ce01eb14c
model-00031-of-00039.safetensors5.23 GBab4724b0496756075ce830caab22f70cdaf0a48b87e135b681f7be934312eea4
model-00032-of-00039.safetensors5.14 GB878a5433b8bbc3c827301a0ea958342fe74001c4162505ee13c3db4910c3e35e
model-00033-of-00039.safetensors5.14 GBed8830a07529bd8fc16f07aef7181bdc856d4cc4bd3ef966e5190d4d30669176
model-00034-of-00039.safetensors5.23 GB8ff86fb4d909c5eb273be8e7b0cb10fac381c2db27b3f17b19ac7ed07e871475
model-00035-of-00039.safetensors5.14 GB13bac897fa8f38ab8dad87daa31dfa6945a1927dbae75a5614447ce7c77b6363
model-00036-of-00039.safetensors5.14 GBa101e05050758ac4ea777e31f5378f1ec906702e244cc3b2492b7df48711930f
model-00037-of-00039.safetensors5.23 GB250a9ace5706100f831d63060c2c74b9c0a3a7fc4b40c02d08c36a6f982c3345
model-00038-of-00039.safetensors5.14 GB2f7a60a53377f0d0fbe0587e53f32649ddaaf9a3c53c28f975e4238445cec4c3
model-00039-of-00039.safetensors1.87 GB900dc2b56471c9b403d02728ab7930573f157edda3b30399645acfa6a4beb176
model.safetensors.index.json325 KB57dc9a95fab9cb2670ec7f57cdf1f66fcb4f7aabe2122c21547213aeb6dea627
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
dfcf4c549d pinned now2026-11-15 05:15 UTC48 files · 199 GB

Use it

$ fw get mlx-community/GLM-4.6-4bit
# manifest sha256 f5ea96b33b71… · 199 GB · 48 files
$ fw verify ./GLM-4.6-4bit mlx-community/GLM-4.6-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/GLM-4.6-4bit.json --dir ./GLM-4.6-4bit $ python3 fw.py verify ./GLM-4.6-4bit ./mlx-community__GLM-4.6-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/GLM-4.6-4bit --revision dfcf4c549df3cd03bd61a7766899cffc79ffe0af --local-dir ./GLM-4.6-4bit
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/GLM-4.6-4bit", revision="dfcf4c549df3cd03bd61a7766899cffc79ffe0af") model = AutoModelForCausalLM.from_pretrained("mlx-community/GLM-4.6-4bit", revision="dfcf4c549df3cd03bd61a7766899cffc79ffe0af", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/GLM-4.6-4bit --revision dfcf4c549df3cd03bd61a7766899cffc79ffe0af

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
2a1bfe79e14feb6a9c4ea1889af2a6a27caada2a5aaf3cb7f2ca988100498737
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-4.6-4bitDate: 2026-11-15Commit: dfcf4c5Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/GLM-4.6-4bit
Pinned commit
dfcf4c549df3cd03bd61a7766899cffc79ffe0af
Manifest
GLM-4.6-4bit.json · .minisig
Manifest sha256
f5ea96b33b71a44b069611a856cd0a71839c9b568cc127f84e31ffec7d1cad5d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:15 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/GLM-4.6-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/GLM-4.6-4bit.json.minisig $ minisign -Vm GLM-4.6-4bit.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

zai-org/GLM-4.6 · 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-4.6-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. GLM-4.6-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/GLM-4.6-4bit

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