# QuantFactory/granite-3b-code-base-128k-GGUF

Model from Hugging Face for text generation: QuantFactory/granite-3b-code-base-128k-GGUF · transformers

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/QuantFactory/granite-3b-code-base-128k-GGUF
- Hosting: hosted (1 file)
- Files: 1 hosted of 16 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 1 file, 2.13 GB
- Full repo upstream: 31.4 GB
- Recommended file: 2.13 GB (Q4_K_M) · granite-3b-code-base-128k.Q4_K_M.gguf
- Parameters: 3B
- Download: https://huggingbay.xyz/artifact/hf-model-quantfactory-granite-3b-code-base-128k-gguf/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-3b-code-base-128k-gguf/download-plan)
- Per-file SHA-256: available for 1 of 1 hosted file via https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-3b-code-base-128k-gguf/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 369
- Stars: 2
- Card completeness: 96%

## Description

External Hugging Face catalog record for QuantFactory/granite-3b-code-base-128k-GGUF. Task: text generation. Library: transformers. Datasets referenced by card metadata: codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA. Includes 12 model-card evaluation signals. Popularity signal at import: 486 downloads and 2 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Referenced datasets: codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA
- Metrics: code_eval
- Paper ids: 2405.04324
- Model-index entries: granite-3b-code-base-128k
- Evaluation signals: 12 model-card eval results
- File hints: 16 upstream file samples

## Evaluation Signals

- HumanEvalSynthesis (Python): pass@1 = 36 (text-generation)
- HumanEvalSynthesis (Average): pass@1 = 30.5 (text-generation)
- HumanEvalExplain (Average): pass@1 = 22.4 (text-generation)
- HumanEvalFix (Average): pass@1 = 19.9 (text-generation)
- RepoQA (Python@16K): pass@1 (thresh=0.5) = 40 (text-generation)
- RepoQA (C++@16K): pass@1 (thresh=0.5) = 36 (text-generation)
- RepoQA (Java@16K): pass@1 (thresh=0.5) = 37 (text-generation)
- RepoQA (TypeScript@16K): pass@1 (thresh=0.5) = 27 (text-generation)
- RepoQA (Rust@16K): pass@1 (thresh=0.5) = 29 (text-generation)
- LCC (Balanced): Exact Match@4K = 54.6 (text-generation)

## Referenced Data

- Dataset: codeparrot/github-code-clean
- Dataset: bigcode/starcoderdata
- Dataset: open-web-math/open-web-math
- Dataset: math-ai/StackMathQA
- Paper: 2405.04324

## File Hints

- .gitattributes (2.5 KB)
- README.md (8.9 KB)
- granite-3b-code-base-128k.Q2_K.gguf (1.2 GB) LFS
- granite-3b-code-base-128k.Q3_K_L.gguf (1.7 GB) LFS
- granite-3b-code-base-128k.Q3_K_M.gguf (1.6 GB) LFS
- granite-3b-code-base-128k.Q3_K_S.gguf (1.4 GB) LFS
- granite-3b-code-base-128k.Q4_0.gguf (1.9 GB) LFS
- granite-3b-code-base-128k.Q4_1.gguf (2.1 GB) LFS
- granite-3b-code-base-128k.Q4_K_M.gguf (2.0 GB) LFS
- granite-3b-code-base-128k.Q4_K_S.gguf (1.9 GB) LFS
- granite-3b-code-base-128k.Q5_0.gguf (2.3 GB) LFS
- granite-3b-code-base-128k.Q5_1.gguf (2.4 GB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-08-28T09:47:20.170Z.
- Open license detected as apache-2.0.
- Model-index metadata found for granite-3b-code-base-128k.
- Model card references dataset context: codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-quantfactory-granite-3b-code-base-128k-gguf
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-3b-code-base-128k-gguf/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-3b-code-base-128k-gguf/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-3b-code-base-128k-gguf/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-quantfactory-granite-3b-code-base-128k-gguf
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-3b-code-base-128k-gguf/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-quantfactory-granite-3b-code-base-128k-gguf&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-3b-code-base-128k-gguf/decentralized-fallbacks