From: ibm-granite <huggingface.co/ibm-granite> Newsgroups: alt.freeweights.graniteSubject: granite-34b-code-base-8k-GGUF Date: 2026-11-15Commit: db10e16Signed: 2DC28CC7B26A283B ✓ Text generation model. Gguf weights, 21.4 GB in all. Published by ibm-granite under Apache-2.0.
granite 21.4 GB granite-34b-code-base-8k-GGUF gguf permissive
Facts Params not stated Size 21.4 GB Formats gguf Task text generation License Apache-2.0 permissive
fw
$ fw get ibm-granite/granite-34b-code-base-8k-GGUF
# manifest sha256 3845bac8f433… · 21.4 GB · 3 files
$ fw verify ./granite-34b-code-base-8k-GGUF ibm-granite/granite-34b-code-base-8k-GGUFHosted (signed) ibm-granite/granite-34b-code-base-8k-GGUF Last check: 2026-11-15 04:03 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 21.4 GB
Weights 21.4 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 04:03 UTC passed
Model card From the publisher at commit
db10e16 . 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-34b-code-base-8k-GGUF#
This is the Q4_K_M converted version of the original ibm-granite/granite-34b-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-34b-code-base-8k-GGUF/granite-34b-code-base.Q4_K_M.gguf -n 128 -p "def generate_random(x: int):" --colorFiles 3 files · 21.4 GB Weights 21.4 GB (GGUF). Sizes and sha256 from the signed manifest.
Hide all 3 files with their sha256 File Size sha256 .gitattributes 1.59 KB 0b1739d7f834d26b8580c1378eae2ce880a8e413c8cd67abec306d2faced71fa README.md 5.91 KB df60a4ac00f2ee1287f3c813bd1130e3a0cba3ea7d88897c6d0f1db5973edfce granite-34b-code-base.Q4_K_M.gguf 21.4 GB 09b956f3dec817a9d1f31b8d7b8ded12c03a53d7ab8409dba4b918383d8ee53f
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents db10e16bac pinned now 2026-11-15 04:03 UTC 3 files · 21.4 GB
Use it fw
$ fw get ibm-granite/granite-34b-code-base-8k-GGUF
# manifest sha256 3845bac8f433… · 21.4 GB · 3 files
$ fw verify ./granite-34b-code-base-8k-GGUF ibm-granite/granite-34b-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-34b-code-base-8k-GGUF.json --dir ./granite-34b-code-base-8k-GGUF
$ python3 fw.py verify ./granite-34b-code-base-8k-GGUF ./ibm-granite__granite-34b-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-34b-code-base-8k-GGUF --revision db10e16bac727ffd53037253b50c04a7f5b8fca5 --local-dir ./granite-34b-code-base-8k-GGUFllama.cpp Download one GGUF variant (granite-34b-code-base.Q4_K_M, 21.4 GB), then serve it.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download ibm-granite/granite-34b-code-base-8k-GGUF --include "granite-34b-code-base.Q4_K_M*" --local-dir ./granite-34b-code-base-8k-GGUF
$ llama-server -m ./granite-34b-code-base-8k-GGUF/granite-34b-code-base.Q4_K_M.ggufOllama Make an Ollama model from the downloaded file.
$ printf 'FROM ./granite-34b-code-base-8k-GGUF/granite-34b-code-base.Q4_K_M.gguf\n' > Modelfile
$ ollama create granite-34b-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 df60a4ac00f2ee1287f3c813bd1130e3a0cba3ea7d88897c6d0f1db5973edfce 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-34b-code-base-8k-GGUF Date: 2026-11-15Commit: db10e16Signed: 2DC28CC7B26A283B ✓
How to verify
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-34b-code-base-8k-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-34b-code-base-8k-GGUF.json.minisig
$ minisign -Vm granite-34b-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-34b-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
