CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.glm / GLM-4.7-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.glmSubject:

GLM-4.7-4bit

Date: 2026-11-15Commit: 0e9f6c4Signed: 2DC28CC7B26A283B ✓

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

352.8B params199GBGLM-4.7-4bitsafetensorspermissive
FactsParams352.8BSize199 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/GLM-4.7-4bit
# manifest sha256 11adf8d4013d… · 199 GB · 47 files
$ fw verify ./GLM-4.7-4bit mlx-community/GLM-4.7-4bit
From sourceHosted (signed)mlx-community/GLM-4.7-4bitLast check: 2026-11-15 05:12 UTC
Get help

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

Quantized of GLM-4.7.

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
47, 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-4.7

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 05:12 UTCpassed

Model card

From the publisher at commit 0e9f6c4. Shown as plain text with links; images open at the publisher.

mlx-community/GLM-4.7-4bit#

This model mlx-community/GLM-4.7-4bit was converted to MLX format from zai-org/GLM-4.7 using mlx-lm version 0.30.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/GLM-4.7-4bit")

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

47 files · 199 GBWeights 199 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 47 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md802 B2c7561b7cb1f79e65b7b31a7da0f418908b2d1e58d0e27af72a915713900ae86
chat_template.jinja3.12 KBd63ad536c3c81880043e22ec7fd08db42b4d8fb7c89c7138bc562bfa25281375
config.json1.30 KB7f79bf5b0a4f789d9f5434df521b2d3a572b87d5191cf69eba16f4b227f402f0
generation_config.json177 B71a6281557b989ff592e7a13fd170b8ab1e5700bac2313df6a64ee1f9286b3cf
model-00001-of-00039.safetensors5.36 GB02234a060d883f4ede1bd429178f78f8ddf38ede3cfc84047e369a7dba5ef43e
model-00002-of-00039.safetensors5.27 GB9306e2fa3fd08af60133fafebb8890bf831c567159bad41541cac13b36a8babb
model-00003-of-00039.safetensors5.14 GB32d4b406a3724f6ea5e9511429213a33ca127911d6a0274e78d2824c45102e3d
model-00004-of-00039.safetensors5.23 GBbe67b8e77e4466a0c524d3731cb0c5502c4ed0349035a6f0029d2b4484ffac13
model-00005-of-00039.safetensors5.14 GB15d266761d408aa599c46d8e88e4defa9bfc01eeacc62b7c1b7fca0955fa1483
model-00006-of-00039.safetensors5.14 GB38a8d1c409d4f25c265cb15ee7a13cb4c7715795dec4f2265b0cec8fc930108c
model-00007-of-00039.safetensors5.23 GBeb1d7a13822166402fa057fc61e4a00e4c2ceb4c36c32ae7edce3d9dd26fe5e3
model-00008-of-00039.safetensors5.14 GBa32cebb6beb8907cdcf77d5bf8ef13e9d37628305d35f7ef738b71c213038958
model-00009-of-00039.safetensors5.14 GB6f7ff3bc7457572fe7e271e09d959526b5faba4ac91cb758faceb867f59dc66d
model-00010-of-00039.safetensors5.23 GBd5692fce5c54bf67e58f61d0af022ee42da3a3c7f4e1c6dc0da6595d88dfa93b
model-00011-of-00039.safetensors5.14 GB1cd4cddaa0fba069a288b34ad241e4adecede698de3a7f5266ad8a561313ecee
model-00012-of-00039.safetensors5.14 GB913b61e092a1982bd1f9f9836f593e223fd4e5eae1944bb67b533f21886fc039
model-00013-of-00039.safetensors5.23 GBd86c90cbf826e40259e1c4ddfc782a1bbd55353fed640eaa7994017ad3aea6fa
model-00014-of-00039.safetensors5.14 GBfbb911ee9e7ba55417e76854fd17c81c168ab1e85ed803a2c5fa1bcc282d05ba
model-00015-of-00039.safetensors5.14 GBb642b9676c31e301a3a98a80ef2e47069a5b7ad4aefc37985367fe34f7542131
model-00016-of-00039.safetensors5.23 GB029e4d30093367763e6d5adbf9eb3b6912894a33c7c79710c3b40390abeb8a46
model-00017-of-00039.safetensors5.14 GB951265da3872ee9ff83fb416aea63664275e6719bfb8c61b1eb423fe2ade0cd4
model-00018-of-00039.safetensors5.14 GBde247f93dbb8e530ebd38ca33475bdc5a85fc0a137e81e6a3e919e59c36f34d6
model-00019-of-00039.safetensors5.23 GBa938caa920e6351819713319758169563f8c11e82d1f625f46dbab074879995c
model-00020-of-00039.safetensors5.14 GB956544febf1fe7e982f4f3aea9eb22489fa1f388d87fadac11a44a9a63b756f2
model-00021-of-00039.safetensors5.14 GB8cd8b2bd7e89a77d08c2ef25f0d19c8cbe439ab47ee718b20db7c139fcbc0ab7
model-00022-of-00039.safetensors5.23 GB7c949d9c71d45af4d065a3d05e6238716e5957be6044a4339d8644d3315fe86b
model-00023-of-00039.safetensors5.14 GB785c036767fcf33f427c51905f761bc5542ef79aa52d12bbe0b67469a64f145d
model-00024-of-00039.safetensors5.14 GBc80a1ef6c2a58c2472ec37fcb9e1cf4649b84bbcf871e30d6f51e2a5ae3bffc7
model-00025-of-00039.safetensors5.23 GB29d3838123d7c9f4b003f1bcf70857a73dfdd12076be55ccdfde8e4a7ff5e028
model-00026-of-00039.safetensors5.14 GB4bd478067db2116b5e4ba65381658e8fd2be9f7e39212948511701ab07168555
model-00027-of-00039.safetensors5.14 GBf5e9b5065004d0a3f44eb66975cf6f3951927618ae4b9f087d3fa6301f6c007b
model-00028-of-00039.safetensors5.23 GB1f844847c116cf77a0b1ba6f7a0e6243909bf76b0fbb29bb96c5715d5fa5d131
model-00029-of-00039.safetensors5.14 GB088bee6fb8727ef95e37b5a3eaf2ce9486e5ed3ab0abb24fa083d4c07df38d72
model-00030-of-00039.safetensors5.14 GB11c4c558d8147e7be5703d67c96d7a1afa2084ddb3cd31a253425fbf51f1fb6e
model-00031-of-00039.safetensors5.23 GBe3fd12104d23d8ba70a96f0ff73585003482e069aaff248e5074898e83e6e542
model-00032-of-00039.safetensors5.14 GB026f41c67377e384403bea0e3b8c5dae80a41d180a90a242f9b694b427ad39e3
model-00033-of-00039.safetensors5.14 GBac74bdc3838bc04d99a4530dc439e6afc6d06bf321d30df55b3388b4c542a1e2
model-00034-of-00039.safetensors5.23 GB4e27f72586445fc440390f2c2b5aaf3027090d2c6637ceb8bf6b4d52efcdceb0
model-00035-of-00039.safetensors5.14 GB51bb48b9fbaaa23a1aaef5408b5de1bac77ea474d2447ea96ae126e86e851dc4
model-00036-of-00039.safetensors5.14 GB985a15e7049c2b37cb5a0606293c992bf310d1bfc1f47fb582cb9ffb5b3253f6
model-00037-of-00039.safetensors5.23 GB67eca1edaa48144ddf1db14e5ebc1d4b2b4793ace6d4d661ac50da81598b08dd
model-00038-of-00039.safetensors5.14 GB54fe54e69db8d4ef286bab7ba021fe78aba4d45961f7008c43f9bf604763c36f
model-00039-of-00039.safetensors1.87 GB7dfc6725f60232f84d21b1777bfecfd39431e0a5963cf457b9f8d99d8d8599b7
model.safetensors.index.json325 KB57dc9a95fab9cb2670ec7f57cdf1f66fcb4f7aabe2122c21547213aeb6dea627
tokenizer.json20.0 MBf0ccf2252fe9cd23ada23a829ec409aab397dbd2ac4f372d3a1a23d1f7c72d6b
tokenizer_config.json1.38 KB74adbb07a8b6553999b1753e2cac54b48fd8a4e866c6b67e792189e4b775a978
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0e9f6c4bab pinned now2026-11-15 05:12 UTC47 files · 199 GB

Use it

$ fw get mlx-community/GLM-4.7-4bit
# manifest sha256 11adf8d4013d… · 199 GB · 47 files
$ fw verify ./GLM-4.7-4bit mlx-community/GLM-4.7-4bit
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-4.7-4bit.json --dir ./GLM-4.7-4bit $ python3 fw.py verify ./GLM-4.7-4bit ./mlx-community__GLM-4.7-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/GLM-4.7-4bit --revision 0e9f6c4babaef5d5fd04c9efc8770ef234b6d576 --local-dir ./GLM-4.7-4bit
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-4.7-4bit", revision="0e9f6c4babaef5d5fd04c9efc8770ef234b6d576") model = AutoModelForCausalLM.from_pretrained("mlx-community/GLM-4.7-4bit", revision="0e9f6c4babaef5d5fd04c9efc8770ef234b6d576", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/GLM-4.7-4bit --revision 0e9f6c4babaef5d5fd04c9efc8770ef234b6d576

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
2c7561b7cb1f79e65b7b31a7da0f418908b2d1e58d0e27af72a915713900ae86
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-4.7-4bitDate: 2026-11-15Commit: 0e9f6c4Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/GLM-4.7-4bit
Pinned commit
0e9f6c4babaef5d5fd04c9efc8770ef234b6d576
Manifest
GLM-4.7-4bit.json · .minisig
Manifest sha256
11adf8d4013dcdd4ecf70bbe3b12f740201db3320f295df4768bdef28054383a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:12 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/GLM-4.7-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/GLM-4.7-4bit.json.minisig $ minisign -Vm GLM-4.7-4bit.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-4.7 · 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-4.7-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. GLM-4.7-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/GLM-4.7-4bit

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