alt.freeweights.glm / GLM-4.5-Air-GGUF

From:

unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.glmSubject:

GLM-4.5-Air-GGUF

Date: 2026-11-14Commit: 506d64aSigned: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 1.93 TB in all. Published by unsloth under MIT.

glm

1.93TBGLM-4.5-Air-GGUFggufpermissive

FactsParamsnot statedSize1.93 TBFormatsggufTasktext generationLicenseMITFrom sourcepermissive

$ fw get unsloth/GLM-4.5-Air-GGUF
# manifest sha256 e71a76290f87… · 1.93 TB · 55 files
$ fw verify ./GLM-4.5-Air-GGUF unsloth/GLM-4.5-Air-GGUF

From sourceHosted (signed)unsloth/GLM-4.5-Air-GGUFLast check: 2026-11-14 21:32 UTC

Run at home 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

Run14 Convert1 Evaluate13 Scan12 Apps58

Runs with

Ranked by fit to this model (gguf), then by GitHub stars.

Text Generation WebUI mistral.rs

Ollama

llama.cpp LocalAI

BitNet llamafile gpu-unlock KoboldCpp PocketPal AI llama-swap ik_llama.cpp

Show all 14

RamaLama Maid

Convert with

ggml

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 1.93 TB
Weights: 38.3 GB (smallest of 27 GGUF variants)
Parameters: not stated
Formats: gguf
Task: text generation
License: MIT (permissive)
Files: 55, each with a sha256
Publisher: unsloth
Added: 2026-11-14
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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-14 21:32 UTC	passed

Model card

From the publisher at commit 506d64a. Shown as plain text with links; images open at the publisher.

Note. Includes Unsloth chat template fixes!

For llama.cpp, use --jinja

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

https://github.com/unslothai/unsloth/ https://discord.gg/unsloth https://docs.unsloth.ai/

GLM-4.5-Air#

Image: image

👋 Join our Discord community.

📖 Check out the GLM-4.5 technical blog.

📍 Use GLM-4.5 API services on Z.ai API Platform (Global) or Zhipu AI Open Platform (Mainland China).

👉 One click to GLM-4.5.

Model Introduction#

The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.

Both GLM-4.5 and GLM-4.5-Air are hybrid reasoning models that provide two modes: thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses.

We have open-sourced the base models, hybrid reasoning models, and FP8 versions of the hybrid reasoning models for both GLM-4.5 and GLM-4.5-Air. They are released under the MIT open-source license and can be used commercially and for secondary development.

As demonstrated in our comprehensive evaluation across 12 industry-standard benchmarks, GLM-4.5 achieves exceptional performance with a score of 63.2, in the 3rd place among all the proprietary and open-source models. Notably, GLM-4.5-Air delivers competitive results at 59.8 while maintaining superior efficiency.

Image: bench

For more eval results, show cases, and technical details, please visit our technical blog. The technical report will be released soon.

The model code, tool parser and reasoning parser can be found in the implementation of transformers, vLLM and SGLang.

Quick Start#

Please refer our github page for more detail.

Files

55 files · 1.93 TBWeights 38.3 GB (smallest of 27 GGUF variants). Sizes and sha256 from the signed manifest.

Show all 55 files with their sha256

File	Size	sha256
.gitattributes	5.80 KB	5cc7b239cde8678282141343b7a327e0acea598d09ddf90d71d82507b920db2c
BF16/GLM-4.5-Air-BF16-00001-of-00005.gguf	49.8 GB	2de50f20eba00175a6d16720ff3023d37a9a129053f50cdd0a83c9d2bc8eff56
BF16/GLM-4.5-Air-BF16-00002-of-00005.gguf	49.8 GB	11dafc83703c8a928c46d041d7d4130ad47e2fbb2110fb6e3d96aaff828c809f
BF16/GLM-4.5-Air-BF16-00003-of-00005.gguf	48.6 GB	0bee6673f84bc0dbc29dc2a199250352970d0baddb71aaff5be1f66906357bf8
BF16/GLM-4.5-Air-BF16-00004-of-00005.gguf	49.8 GB	f49c9a8a73b62a1cbe479711c322a7da73fec97ee9f88bb49f9a15518e309dc9
BF16/GLM-4.5-Air-BF16-00005-of-00005.gguf	23.0 GB	874d7234d61b22c1b4663bd52e2391274b2e4b5470adddfb05629bc2cebdd45a
GLM-4.5-Air-Q2_K.gguf	45.3 GB	c5b679b541d995478467bf4218098dee08dfc054f80cdbd3cdda8a1cae69e4d1
GLM-4.5-Air-Q2_K_L.gguf	45.5 GB	7d11efe2aa2eaaa1458dbae971f9fcd933ce3431498eb62a2f2a24fd20d797f2
GLM-4.5-Air-UD-IQ1_M.gguf	40.1 GB	b0e6a30101c8f8e4c4b655b910e0c3a1e00fbd2d94d110ccd6a448074578a829
GLM-4.5-Air-UD-IQ1_S.gguf	38.5 GB	4491e4427ecbf93588f9f23483028ff1e7a3b6f63a0602fcb353f623bf0412ab
GLM-4.5-Air-UD-IQ2_M.gguf	44.4 GB	33d80296f3b0ef0463985a6fe6dc2ad3a4260b09c549487623c1f35f7b6193fd
GLM-4.5-Air-UD-IQ2_XXS.gguf	42.7 GB	63158240af293e1b34eb2c4ed3a0256dce3a3324f55fbe141698c47fd4b4a7a8
GLM-4.5-Air-UD-Q2_K_XL.gguf	47.4 GB	609fe51f04b1a17941fb3549de50b6fa4137a32641ca23d88e7f1f12ad5deaef
GLM-4.5-Air-UD-TQ1_0.gguf	38.3 GB	a9c578fe9d80668ce4850ed0f09a7238f53546f81821f558add526cd3666a1bf
IQ4_NL/GLM-4.5-Air-IQ4_NL-00001-of-00002.gguf	50.0 GB	c01c0ae4cceeb0be681dac86deb6c46b565cfd6d2eac03ea72c63cb9261bb3ec
IQ4_NL/GLM-4.5-Air-IQ4_NL-00002-of-00002.gguf	12.7 GB	c9f160f3cc9b0b78d66642e0cde1a8d056207bbddc4df89cdfba3cdfb9b4cb30
IQ4_XS/GLM-4.5-Air-IQ4_XS-00001-of-00002.gguf	49.9 GB	602c30095517b6b25b8b28e797f3544800b5026a2cbfd73ed9a82cb56bdf34c5
IQ4_XS/GLM-4.5-Air-IQ4_XS-00002-of-00002.gguf	10.6 GB	1077f5127deb87752d609c5c51c3749081f7d5b49e6627df71fb7977b6b1ea32
Q3_K_M/GLM-4.5-Air-Q3_K_M-00001-of-00002.gguf	50.0 GB	c5b59ad366fd7376cef63243ad7014e06ee4260e5854b5ac367699b3b2267d91
Q3_K_M/GLM-4.5-Air-Q3_K_M-00002-of-00002.gguf	7.24 GB	da762539c9446edd159f58b6116aa65109d2d73b398aa2089a302c5675f63357
Q3_K_S/GLM-4.5-Air-Q3_K_S-00001-of-00002.gguf	49.8 GB	4722e5e28e4d586220d8d8a141d1a1038bbf9b47198eac4a78cd9502075adee5
Q3_K_S/GLM-4.5-Air-Q3_K_S-00002-of-00002.gguf	2.82 GB	084f1abb2d2908ec0f4100cc0e7a787b0928e36aed5d6444820a3ce92951f379
Q4_0/GLM-4.5-Air-Q4_0-00001-of-00002.gguf	49.7 GB	a74d4128af237efefc1564eeafb2c4062c3672c96f7ae5d0e76040b8400ce6e4
Q4_0/GLM-4.5-Air-Q4_0-00002-of-00002.gguf	13.0 GB	f793597f2a8ae4e5ff485c2f9425d2bbc33dedf2c2aa80b0fc2afda22732e2d6
Q4_1/GLM-4.5-Air-Q4_1-00001-of-00002.gguf	49.6 GB	4e986bc9ed335a7ceaf254c82de177b622d079d48943ed74e4c31f5cfb521702
Q4_1/GLM-4.5-Air-Q4_1-00002-of-00002.gguf	19.8 GB	658bbba6e191179bb0931e98091a6e1bbeaebc73225602b1ff2c424fa0171de7
Q4_K_M/GLM-4.5-Air-Q4_K_M-00001-of-00002.gguf	50.0 GB	3e7e5d25a6db33b7c90f8c5203d6f490d6c0a4f04a46f228af0e33727db5df5e
Q4_K_M/GLM-4.5-Air-Q4_K_M-00002-of-00002.gguf	23.0 GB	ac6e50523d45c53faf3bf72d8fe109f3dd54bc6abe98a7773a3636112ead82a6
Q4_K_S/GLM-4.5-Air-Q4_K_S-00001-of-00002.gguf	49.9 GB	c0b7cdaec3fe4166731f352f85eae4d85a855c89582794de93055cbcb805e034
Q4_K_S/GLM-4.5-Air-Q4_K_S-00002-of-00002.gguf	17.1 GB	a8cd861ea9a03029d3779c446427cf241a922a082d181c7b94f1ee9941b53033
Q5_K_M/GLM-4.5-Air-Q5_K_M-00001-of-00002.gguf	49.9 GB	fc28dbc9e6e2936af9943b2d3233bc0a522e669be418957f42e5b2629fed0ad7
Q5_K_M/GLM-4.5-Air-Q5_K_M-00002-of-00002.gguf	33.6 GB	a52bf87db54a21c120b2306ebcd61bc1e4200dbee607973ee58b28591cc1c652
Q5_K_S/GLM-4.5-Air-Q5_K_S-00001-of-00002.gguf	49.9 GB	8ebe86f0abf7b78c7408f358f1456111e4e45ec86c5b0d6302c003deb1297967
Q5_K_S/GLM-4.5-Air-Q5_K_S-00002-of-00002.gguf	28.5 GB	efe1784838ed629e9d3ee0b107402277ad773ffcbbf7c9a68ae554d95431c444
Q6_K/GLM-4.5-Air-Q6_K-00001-of-00002.gguf	49.7 GB	e51e8d925eabcf84f05bac6954fbbbf9113065fb65ae0b7cd11e40ff0dcbe4ec
Q6_K/GLM-4.5-Air-Q6_K-00002-of-00002.gguf	49.3 GB	02f87aebcc281c012801e4678a54f8503eaf9752cb135b6b3f882d1613fe2fec
Q8_0/GLM-4.5-Air-Q8_0-00001-of-00003.gguf	49.8 GB	8a58096ec777113d5ee396af4198b6b0aeb91d9d02d933f44b310c1645a4a973
Q8_0/GLM-4.5-Air-Q8_0-00002-of-00003.gguf	49.8 GB	dd9da13844bd2d9148515618228e654727d7438db062163ffb55d0ac4a2ba8d8
Q8_0/GLM-4.5-Air-Q8_0-00003-of-00003.gguf	17.9 GB	f9674c7541e7641f6de6c41fcc62f5bcf2e312aff1c4e6d8d2e8927a8cef77c6
README.md	3.74 KB	2cc23c895050f4599eab08cdd7c2ecb1a1e90ebd9652129a34927538855edffc
UD-IQ3_XXS/GLM-4.5-Air-UD-IQ3_XXS-00001-of-00002.gguf	49.7 GB	6c9603e6a8db6effbc8dd6a5dd8d6f625f0d6c5ef7eabbff37f12d739cba590a
UD-IQ3_XXS/GLM-4.5-Air-UD-IQ3_XXS-00002-of-00002.gguf	1.70 GB	203a59c0c3a184adfce5f8454b1cdd3e63a7b90ddb010871d24d08c3cea402c8
UD-Q3_K_XL/GLM-4.5-Air-UD-Q3_K_XL-00001-of-00002.gguf	49.9 GB	1c24976f0ba51fcd5fc21365e82cf4d2b08d1be9de4247d2842e410a50fd4b2c
UD-Q3_K_XL/GLM-4.5-Air-UD-Q3_K_XL-00002-of-00002.gguf	4.86 GB	b145bbd431b0c4a6816094403286f8250b4581a7e39baf4f76b49244a4a489f4
UD-Q4_K_XL/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002.gguf	49.6 GB	1acd6d4acdb4f463c9a61696cb7e830e1a34134e610b573e87a4397adcd90bd7
UD-Q4_K_XL/GLM-4.5-Air-UD-Q4_K_XL-00002-of-00002.gguf	18.1 GB	8e220a3cdf4e19763cc7a5fd0a6215f1da1b3fda1306e64e88456d045c2007f8
UD-Q5_K_XL/GLM-4.5-Air-UD-Q5_K_XL-00001-of-00002.gguf	49.9 GB	8c939530e31b994984138df92eb26d5c7a0869c118ec9f724773d4e703ad589e
UD-Q5_K_XL/GLM-4.5-Air-UD-Q5_K_XL-00002-of-00002.gguf	32.9 GB	f2b621ee8416ea4172e7fc9c3d9b1271eed5f6cb083f1b030e65fd3b85a1c6c5
UD-Q6_K_XL/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003.gguf	49.8 GB	9337126afdf29fbaf6db2d904fcff382d90832b3703ecc983703f5b4331a1be7
UD-Q6_K_XL/GLM-4.5-Air-UD-Q6_K_XL-00002-of-00003.gguf	49.5 GB	6a8946f9d7edd3d24ff9be5d5fe99f041e3c0ef1936e2b57db4b87e8ddb00a8d
UD-Q6_K_XL/GLM-4.5-Air-UD-Q6_K_XL-00003-of-00003.gguf	2.27 GB	999c62a3e08cd0266c64229644c47f16c065771b09f7ec695b6c27e7990b6d27
UD-Q8_K_XL/GLM-4.5-Air-UD-Q8_K_XL-00001-of-00003.gguf	49.8 GB	06d3e870baf439d43b336cc934d5b2a7c2ad1086e220ec518c4f9e30610f775f
UD-Q8_K_XL/GLM-4.5-Air-UD-Q8_K_XL-00002-of-00003.gguf	50.0 GB	b997898f6d4d0c1229f95bfc223214961806688863a80477ef70f2acc0ba9a70
UD-Q8_K_XL/GLM-4.5-Air-UD-Q8_K_XL-00003-of-00003.gguf	28.0 GB	d4caf5899bc9aa20e70fa6fe4db78e545062b6193a14a75a1e235fd030dfcc2f
imatrix_unsloth.gguf_file	228 MB	75ab12d9ae13dac5a83cc7b6e47f882d29cb7c97ce47e498dc2df23ede23ce1a

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
506d64aa8c pinned now manifest updated, same commit	2026-11-14 21:32 UTC	55 files · 1.93 TB
506d64aa8c	2026-11-14 21:32 UTC	55 files · 1.93 TB

Use it

$ fw get unsloth/GLM-4.5-Air-GGUF
# manifest sha256 e71a76290f87… · 1.93 TB · 55 files
$ fw verify ./GLM-4.5-Air-GGUF unsloth/GLM-4.5-Air-GGUF

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/GLM-4.5-Air-GGUF.json --dir ./GLM-4.5-Air-GGUF
$ python3 fw.py verify ./GLM-4.5-Air-GGUF ./unsloth__GLM-4.5-Air-GGUF.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/GLM-4.5-Air-GGUF --revision 506d64aa8c5cfe9dbbf00bc7a15739438f83204d --local-dir ./GLM-4.5-Air-GGUF

llama.cppDownload one GGUF variant (GLM-4.5-Air-UD-TQ1_0, 38.3 GB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/GLM-4.5-Air-GGUF --include "GLM-4.5-Air-UD-TQ1_0*" --local-dir ./GLM-4.5-Air-GGUF
$ llama-server -m ./GLM-4.5-Air-GGUF/GLM-4.5-Air-UD-TQ1_0.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./GLM-4.5-Air-GGUF/GLM-4.5-Air-UD-TQ1_0.gguf\n' > Modelfile
$ ollama create glm-4.5-air-gguf -f Modelfile

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. 2026-11-14
Text in: README.md
Text sha256: 2cc23c895050f4599eab08cdd7c2ecb1a1e90ebd9652129a34927538855edffc
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:

unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.glmSubject: GLM-4.5-Air-GGUFDate: 2026-11-14Commit: 506d64aSigned: 2DC28CC7B26A283B ✓

Upstream: unsloth/GLM-4.5-Air-GGUF
Pinned commit: 506d64aa8c5cfe9dbbf00bc7a15739438f83204d
Manifest: GLM-4.5-Air-GGUF.json · .minisig
Manifest sha256: e71a76290f87541a85e6b12b3e922c9804b3cbd1e903c8a39898a12239371f80
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-14 21:32 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/GLM-4.5-Air-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/unsloth/GLM-4.5-Air-GGUF.json.minisig
$ minisign -Vm GLM-4.5-Air-GGUF.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 unsloth/GLM-4.5-Air-GGUF

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-GGUF.json. Provenance. Takedown history: none.

Source

huggingface.co/unsloth/GLM-4.5-Air-GGUF

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