From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.graniteSubject: granite-4.0-h-350m-8bit Date: 2026-11-15Commit: 754e5aeSigned: 2DC28CC7B26A283B ✓ Text generation model with 340M parameters. Safetensors weights, 372 MB in all. Published by mlx-community under Apache-2.0.
340M params 372 MB granite-4.0-h-350m-8bit safetensors permissive Facts Params 340M Size 372 MB Formats safetensors Task text generation License Apache-2.0 permissive
fw
$ fw get mlx-community/granite-4.0-h-350m-8bit
# manifest sha256 5bc2f22949e9… · 372 MB · 12 files
$ fw verify ./granite-4.0-h-350m-8bit mlx-community/granite-4.0-h-350m-8bitHosted (signed) mlx-community/granite-4.0-h-350m-8bit Last check: 2026-11-15 05:12 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of granite-4.0-h-350m .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 372 MB
Weights 362 MB (safetensors)
Parameters 340M
Formats safetensors
Task text generation
License Apache-2.0 (permissive)
Files 12, each with a sha256
Publisher mlx-community
Added 2026-11-15
Section alt.freeweights.granite Lineage
Original release from the publisher.
Base model: ibm-granite/granite-4.0-h-350m
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 huggingface.co 2026-11-15 05:12 UTC passed
Model card From the publisher at commit
754e5ae . Shown as plain text with links; images open at the publisher.
This model mlx-community/granite-4.0-h-350m-8bit was converted to MLX format from ibm-granite/granite-4.0-h-350m using mlx-lm version 0.28.4 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/granite-4.0-h-350m-8bit")
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 12 files · 372 MB Weights 362 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 904 B 304a487d97dd0d5a1cdbe04b802e1d6143e985aa70dcf4142e5217d18609ca21 chat_template.jinja 6.42 KB 9524df67b77a7b25a2dfee898f75b316a157eb9d855b51e32aeac79d7c8a83ce config.json 2.15 KB 8b77fe960f8f05ec7d50944a9da6bf60290714241e86c619f09e2ec20805005b generation_config.json 147 B 7c04cb9d2ba771f7528fba5a7104999cdaf7566d02b5fbd58472829f62716177 merges.txt 917 KB b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502 model.safetensors 362 MB 63be5889f8831acb0e3d738da218c860246513d675dafd044e9ec8293a632a35 model.safetensors.index.json 50.3 KB 1270737fb192e3b015bbfb85ebff57c01dd1a31e7b1a59ec493e1157dd44760f special_tokens_map.json 579 B c08676c49fd7969a3130f72be6d4bf34da66aa484a6e21dffe359893a1bd5f2e tokenizer.json 7.15 MB e2bad66439538cb4d5a7580680932432ed9ece9d3b8577e675512bdf11599253 tokenizer_config.json 17.7 KB a5ec5daab12ba090a90f3dd169c8f9c275557013a87b9c1258dc7cb497a35c86 vocab.json 1.61 MB 8af71076de8b0b626eed0f4c984faf0a7c062479164b2a31308a948524d4f69c
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 754e5ae403 pinned now 2026-11-15 05:12 UTC 12 files · 372 MB
Use it fw
$ fw get mlx-community/granite-4.0-h-350m-8bit
# manifest sha256 5bc2f22949e9… · 372 MB · 12 files
$ fw verify ./granite-4.0-h-350m-8bit mlx-community/granite-4.0-h-350m-8bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/granite-4.0-h-350m-8bit.json --dir ./granite-4.0-h-350m-8bit
$ python3 fw.py verify ./granite-4.0-h-350m-8bit ./mlx-community__granite-4.0-h-350m-8bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/granite-4.0-h-350m-8bit --revision 754e5ae403ffa03922e36332ca5e528f14464a1b --local-dir ./granite-4.0-h-350m-8bittransformers Load 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/granite-4.0-h-350m-8bit", revision="754e5ae403ffa03922e36332ca5e528f14464a1b")
model = AutoModelForCausalLM.from_pretrained("mlx-community/granite-4.0-h-350m-8bit", revision="754e5ae403ffa03922e36332ca5e528f14464a1b", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/granite-4.0-h-350m-8bit --revision 754e5ae403ffa03922e36332ca5e528f14464a1bLicense 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 304a487d97dd0d5a1cdbe04b802e1d6143e985aa70dcf4142e5217d18609ca21 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: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.graniteSubject: granite-4.0-h-350m-8bit Date: 2026-11-15Commit: 754e5aeSigned: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.0-h-350m-8bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.0-h-350m-8bit.json.minisig
$ minisign -Vm granite-4.0-h-350m-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 No model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/granite-4.0-h-350m-8bitOpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
6.8B params 27.4 GB GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1 safetensors permissive Facts Params 6.8B Size 27.4 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: ibm-granite <huggingface.co/ibm-granite> Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1 6.8B params 27.4 GB GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed2 safetensors permissive Facts Params 6.8B Size 27.4 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: ibm-granite <huggingface.co/ibm-granite> Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed2 6.8B params 27.4 GB GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3 safetensors permissive Facts Params 6.8B Size 27.4 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: ibm-granite <huggingface.co/ibm-granite> Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3 6.8B params 27.4 GB GneissWeb.7B_ablation_model_on_350B_FineWeb.seed1 safetensors permissive Facts Params 6.8B Size 27.4 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: ibm-granite <huggingface.co/ibm-granite> Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed1 6.8B params 27.4 GB GneissWeb.7B_ablation_model_on_350B_FineWeb.seed2 safetensors permissive Facts Params 6.8B Size 27.4 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: ibm-granite <huggingface.co/ibm-granite> Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed2 6.8B params 27.4 GB GneissWeb.7B_ablation_model_on_350B_FineWeb.seed3 safetensors permissive Facts Params 6.8B Size 27.4 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: ibm-granite <huggingface.co/ibm-granite> Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed3
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.graniteSubject: 
