From: ibm-granite <huggingface.co/ibm-granite> Newsgroups: alt.freeweights.graniteSubject: granite-4.2-3b-fp8 Date: 2026-11-15Commit: 579eab4Signed: 2DC28CC7B26A283B ✓ Text generation model with 3.7B parameters. Safetensors weights, 4.19 GB in all. Published by ibm-granite under Apache-2.0.
3.7B params 4.19 GB granite-4.2-3b-fp8 safetensors permissive
Facts Params 3.7B Size 4.19 GB Formats safetensors Task text generation License Apache-2.0 permissive
fw
$ fw get ibm-granite/granite-4.2-3b-fp8
# manifest sha256 f98769b5cb38… · 4.19 GB · 14 files
$ fw verify ./granite-4.2-3b-fp8 ibm-granite/granite-4.2-3b-fp8Hosted (signed) ibm-granite/granite-4.2-3b-fp8 Last check: 2026-11-15 04:58 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of granite-4.2-3b .
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 4.19 GB
Weights 4.18 GB (safetensors)
Parameters 3.7B
Formats safetensors
Task text generation
License Apache-2.0 (permissive)
Files 14, each with a sha256
Publisher ibm-granite
Added 2026-11-15
Section alt.freeweights.granite Lineage
Original release from the publisher.
Base model: ibm-granite/granite-4.2-3b
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 04:58 UTC passed
Model card From the publisher at commit
579eab4 . Shown as plain text with links; images open at the publisher.
Files 14 files · 4.19 GB Weights 4.18 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 365 B 7286670cdef38c46163fb88748960c32d576f7dcb92c0e8d46e52c1d9b29b7c2 chat_template.jinja 9.01 KB f0ba43f79b3cabca5e5a7584c77aec92f49feae45cdf7779c87d9fc54cd90258 config.json 2.21 KB fdd583ae03a9a2995c16cce455941cde0f31116dd2bc1285b03fa4a5f59720aa generation_config.json 207 B 1b9baf0a7959d31d7fb58ff6b506c27d09a73d395cadccc7e6dd1d4b7e43fd9d granite_thinking_parser.py 4.65 KB cd5eef99f559f33dc402e0475174a97dcb43724d7e810149c702e9bbc473048a merges.txt 917 KB b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502 model.safetensors 4.18 GB c9ac12e28a8e48eb53442040f35e52be9978c4e2499766b1f5502e5c1f117eef model.sig 10.8 KB d3685087c051352a73a24fb6d73316e429957dab4a90e354c5a61771611ac463 recipe.yaml 176 B 202b71abfb88a3e1bddc2f79f4c3742171af6bd60c214573c4610b3b1817c91f special_tokens_map.json 563 B e9435fefd6d838fd9fcbbc44b97a8e3ff322be7f6dfb7e4fd2468586574bb52b tokenizer.json 7.15 MB 883975314d58743726347caaf2c32ac89afd5ad57222cffbc4f052f2ab27b2d7 tokenizer_config.json 17.7 KB 2007f26df166ed10a2d6fa881c1c8f3cdd151e451469f59b274897f14449835f vocab.json 1.61 MB a1be0c1e0a89b5bacda6af6f8b63df09668cb8d1f656229ee9123140c9507810
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 579eab4470 pinned now 2026-11-15 04:58 UTC 14 files · 4.19 GB
Use it fw
$ fw get ibm-granite/granite-4.2-3b-fp8
# manifest sha256 f98769b5cb38… · 4.19 GB · 14 files
$ fw verify ./granite-4.2-3b-fp8 ibm-granite/granite-4.2-3b-fp8fw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/ibm-granite/granite-4.2-3b-fp8.json --dir ./granite-4.2-3b-fp8
$ python3 fw.py verify ./granite-4.2-3b-fp8 ./ibm-granite__granite-4.2-3b-fp8.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download ibm-granite/granite-4.2-3b-fp8 --revision 579eab44700093cf415d70534060b653dc4d6b45 --local-dir ./granite-4.2-3b-fp8transformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("ibm-granite/granite-4.2-3b-fp8", revision="579eab44700093cf415d70534060b653dc4d6b45")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.2-3b-fp8", revision="579eab44700093cf415d70534060b653dc4d6b45", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve ibm-granite/granite-4.2-3b-fp8 --revision 579eab44700093cf415d70534060b653dc4d6b45License 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 7286670cdef38c46163fb88748960c32d576f7dcb92c0e8d46e52c1d9b29b7c2 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: ibm-granite <huggingface.co/ibm-granite> Newsgroups: alt.freeweights.graniteSubject: granite-4.2-3b-fp8 Date: 2026-11-15Commit: 579eab4Signed: 2DC28CC7B26A283B ✓
Upstream ibm-granite/granite-4.2-3b-fp8 Pinned commit 579eab44700093cf415d70534060b653dc4d6b45 Manifest granite-4.2-3b-fp8.json · .minisig Manifest sha256 f98769b5cb38ea22289671a6078b0c0855d268de700265ae32365160dc87f34d Signature minisign, Ed25519, key 2DC28CC7B26A283B Created 2026-11-15 04:58 UTC Generator freeweights-manifest/0.1.0 Takedowns None. How to verify
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-4.2-3b-fp8.json
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-4.2-3b-fp8.json.minisig
$ minisign -Vm granite-4.2-3b-fp8.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 ibm-granite/granite-4.2-3b-fp8Open 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
