CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.granite / granite-4.0-h-small-MLX-8bit
From: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.graniteSubject:

granite-4.0-h-small-MLX-8bit

Date: 2026-11-15Commit: 274fe67Signed: 2DC28CC7B26A283B ✓

Text generation model with 32.2B parameters. Safetensors weights, 34.2 GB in all. Published by lmstudio-community under Apache-2.0.

32.2B params34.2GBgranite-4.0-h-small-MLX-8bitsafetensorspermissive
FactsParams32.2BSize34.2 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get lmstudio-community/granite-4.0-h-small-MLX-8bit
# manifest sha256 d7ffa4f78ddc… · 34.2 GB · 18 files
$ fw verify ./granite-4.0-h-small-MLX-8bit lmstudio-community/granite-4.0-h-small-MLX-8bit
From sourceHosted (signed)lmstudio-community/granite-4.0-h-small-MLX-8bitLast check: 2026-11-15 05:06 UTC
Run at homeGet help

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

Quantized of granite-4.0-h-small.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
34.2 GB
Weights
34.2 GB (safetensors)
Parameters
32.2B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
lmstudio-community
Added
2026-11-15
Section
alt.freeweights.granite
Lineage

Original release from the publisher.

Base model: ibm-granite/granite-4.0-h-small

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 05:06 UTCpassed

Model card

From the publisher at commit 274fe67. Shown as plain text with links; images open at the publisher.

💫 Community Model> granite-4.0-h-small by ibm-granite#

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Model creator: ibm-granite

Original model: granite-4.0-h-small

MLX quantization: provided by LM Studio team using mlx_lm

Technical Details#

8-bit quantized version of granite-4.0-h-small using MLX, optimized for Apple Silicon.

Special thanks#

🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.

Disclaimers#

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Files

18 files · 34.2 GBWeights 34.2 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md2.25 KBee8bc860db618dc24eaa8c8bab8d887c9d33006c494015134cf40e06df6c247c
chat_template.jinja6.10 KBfed2756d2d24e127b951dcf139d0b03ab7db8ef23a456128ebc9c2db4901d476
config.json12.0 KB515905bb96b03b5a24302000f396429be315104892f9c03efe503a3221713846
generation_config.json147 B7c04cb9d2ba771f7528fba5a7104999cdaf7566d02b5fbd58472829f62716177
merges.txt917 KBb6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502
model-00001-of-00007.safetensors5.24 GB0f51f497476d7eff0c6e20136f3403314c1c01126341f6727da922de0141ed21
model-00002-of-00007.safetensors5.35 GB369393e03da0c0af98cbea5a4a1f041ea9e61d6fb3d5c3c14b1dae5857425493
model-00003-of-00007.safetensors5.17 GB69467e3e5f2c24ce8c719c3a682731336922ff0e0f3bd18b73ffc0d69fb9ffe8
model-00004-of-00007.safetensors5.35 GB47ef896894a2df5d9f5a825337c83716354dc18c70b146381778f7eff97f240d
model-00005-of-00007.safetensors5.28 GBf74f99884246133fdb0ac806843e2d2c01651367b2714ea4faef5269afae294b
model-00006-of-00007.safetensors5.36 GBe7998c6e689686a0ac9815f464315043c0e4fc650bd780e3ec32f8153cdd776a
model-00007-of-00007.safetensors2.48 GB971f6b8e4ed07aec947351e5d00068e7657c46a96bddd5bf974dae9c45103cb9
model.safetensors.index.json120 KB63321c883d216656fd44691b2fcf10549c7be99609befa554d4866c1fe4c0633
special_tokens_map.json579 Bc08676c49fd7969a3130f72be6d4bf34da66aa484a6e21dffe359893a1bd5f2e
tokenizer.json7.15 MBe2bad66439538cb4d5a7580680932432ed9ece9d3b8577e675512bdf11599253
tokenizer_config.json23.9 KB8b1da66e4d60ce8441553d41b72925fe437e563fc3c448ebb4fc1229f647c00b
vocab.json1.61 MB8af71076de8b0b626eed0f4c984faf0a7c062479164b2a31308a948524d4f69c
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
274fe6768a pinned now2026-11-15 05:06 UTC18 files · 34.2 GB

Use it

$ fw get lmstudio-community/granite-4.0-h-small-MLX-8bit
# manifest sha256 d7ffa4f78ddc… · 34.2 GB · 18 files
$ fw verify ./granite-4.0-h-small-MLX-8bit lmstudio-community/granite-4.0-h-small-MLX-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/lmstudio-community/granite-4.0-h-small-MLX-8bit.json --dir ./granite-4.0-h-small-MLX-8bit $ python3 fw.py verify ./granite-4.0-h-small-MLX-8bit ./lmstudio-community__granite-4.0-h-small-MLX-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/granite-4.0-h-small-MLX-8bit --revision 274fe6768a06d865f6113b474ed7414aff4613a9 --local-dir ./granite-4.0-h-small-MLX-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("lmstudio-community/granite-4.0-h-small-MLX-8bit", revision="274fe6768a06d865f6113b474ed7414aff4613a9") model = AutoModelForCausalLM.from_pretrained("lmstudio-community/granite-4.0-h-small-MLX-8bit", revision="274fe6768a06d865f6113b474ed7414aff4613a9", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve lmstudio-community/granite-4.0-h-small-MLX-8bit --revision 274fe6768a06d865f6113b474ed7414aff4613a9
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
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
ee8bc860db618dc24eaa8c8bab8d887c9d33006c494015134cf40e06df6c247c
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: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.graniteSubject: granite-4.0-h-small-MLX-8bitDate: 2026-11-15Commit: 274fe67Signed: 2DC28CC7B26A283B ✓
Upstream
lmstudio-community/granite-4.0-h-small-MLX-8bit
Pinned commit
274fe6768a06d865f6113b474ed7414aff4613a9
Manifest
granite-4.0-h-small-MLX-8bit.json · .minisig
Manifest sha256
d7ffa4f78ddc81572de186c45a013debb737ec7b7b7ea284bdbf05458b97fa37
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:06 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/granite-4.0-h-small-MLX-8bit.json $ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/granite-4.0-h-small-MLX-8bit.json.minisig $ minisign -Vm granite-4.0-h-small-MLX-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

ibm-granite/granite-4.0-h-small · 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 lmstudio-community/granite-4.0-h-small-MLX-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. granite-4.0-h-small-MLX-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/lmstudio-community/granite-4.0-h-small-MLX-8bit

Related models

All of alt.freeweights.granite →
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed2
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed1
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed2
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed3