From: ibm-granite <huggingface.co/ibm-granite> Newsgroups: alt.freeweights.graniteSubject: granite-20b-code-base-8k-GGUF Date: 2026-11-15Commit: 0629b8cSigned: 2DC28CC7B26A283B ✓ Text generation model. Gguf weights, 12.8 GB in all. Published by ibm-granite under Apache-2.0.
granite 12.8 GB granite-20b-code-base-8k-GGUF gguf permissive
Facts Params not stated Size 12.8 GB Formats gguf Task text generation License Apache-2.0 permissive
fw
$ fw get ibm-granite/granite-20b-code-base-8k-GGUF
# manifest sha256 82a0d48fb4a1… · 12.8 GB · 3 files
$ fw verify ./granite-20b-code-base-8k-GGUF ibm-granite/granite-20b-code-base-8k-GGUFHosted (signed) ibm-granite/granite-20b-code-base-8k-GGUF Last check: 2026-11-15 04:04 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Works with
Runs with Ranked by fit to this model (gguf), then by GitHub stars.
Show all 14
Overview
Size 12.8 GB
Weights 12.8 GB (GGUF)
Parameters not stated
Formats gguf
Task text generation
License Apache-2.0 (permissive)
Files 3, each with a sha256
Publisher ibm-granite
Added 2026-11-15
Section alt.freeweights.granite Lineage
Original release from the publisher.
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 04:04 UTC passed
Model card From the publisher at commit
0629b8c . Shown as plain text with links; images open at the publisher.
⚠️ DEPRECATION WARNING ⚠️#
⚠️ NOT RECOMMENDED FOR USE IN NEW PROJECTS ⚠️#
New applications/projects should use the latest mainline Granite language model family, whose code capabilities supercede this model. This model is being made available strictly for historical/scientific purposes. Please see our Granite Collections for the latest Granite releases.
Image: image/png
ibm-granite/granite-20b-code-base-8k-GGUF#
This is the Q4_K_M converted version of the original ibm-granite/granite-20b-code-base-8koriginal model card for more details.
Use with llama.cpp#
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
# install
make
# run generation
./main -m granite-20b-code-base-8k-GGUF/granite-20b-code-base.Q4_K_M.gguf -n 128 -p "def generate_random(x: int):" --colorFiles 3 files · 12.8 GB Weights 12.8 GB (GGUF). Sizes and sha256 from the signed manifest.
Hide all 3 files with their sha256 File Size sha256 .gitattributes 1.59 KB c2d43cb3f63989d122b971c2d2a66755a4b0b14ff15e1a444e49625382162cbb README.md 5.93 KB 2423052748c5faf34f2e39b9a61d7b8efda1e66dc41eb77aa96e74b571092113 granite-20b-code-base.Q4_K_M.gguf 12.8 GB f85769a9438b4f7a42377223aa0fbfc4cedc3e2e142259243ba73730d816dc7a
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 0629b8c5cb pinned now 2026-11-15 04:04 UTC 3 files · 12.8 GB
Use it fw
$ fw get ibm-granite/granite-20b-code-base-8k-GGUF
# manifest sha256 82a0d48fb4a1… · 12.8 GB · 3 files
$ fw verify ./granite-20b-code-base-8k-GGUF ibm-granite/granite-20b-code-base-8k-GGUFfw.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-20b-code-base-8k-GGUF.json --dir ./granite-20b-code-base-8k-GGUF
$ python3 fw.py verify ./granite-20b-code-base-8k-GGUF ./ibm-granite__granite-20b-code-base-8k-GGUF.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download ibm-granite/granite-20b-code-base-8k-GGUF --revision 0629b8c5cb57028b6954ef7f94e285fee68550a2 --local-dir ./granite-20b-code-base-8k-GGUFllama.cpp Download one GGUF variant (granite-20b-code-base.Q4_K_M, 12.8 GB), then serve it.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download ibm-granite/granite-20b-code-base-8k-GGUF --include "granite-20b-code-base.Q4_K_M*" --local-dir ./granite-20b-code-base-8k-GGUF
$ llama-server -m ./granite-20b-code-base-8k-GGUF/granite-20b-code-base.Q4_K_M.ggufOllama Make an Ollama model from the downloaded file.
$ printf 'FROM ./granite-20b-code-base-8k-GGUF/granite-20b-code-base.Q4_K_M.gguf\n' > Modelfile
$ ollama create granite-20b-code-base-8k-gguf -f ModelfileLicense 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 2423052748c5faf34f2e39b9a61d7b8efda1e66dc41eb77aa96e74b571092113 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-20b-code-base-8k-GGUF Date: 2026-11-15Commit: 0629b8cSigned: 2DC28CC7B26A283B ✓
How to verify
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-20b-code-base-8k-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-20b-code-base-8k-GGUF.json.minisig
$ minisign -Vm granite-20b-code-base-8k-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 No related models in this catalog. Nothing here lists this model as its parent, and it names no parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download ibm-granite/granite-20b-code-base-8k-GGUFOpen 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
