# QuantFactory/granite-8b-code-instruct-128k-GGUF

Model from Hugging Face for text generation: QuantFactory/granite-8b-code-instruct-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-8b-code-instruct-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, 4.88 GB
- Full repo upstream: 72.1 GB
- Recommended file: 4.88 GB (Q4_K_M) · granite-8b-code-instruct-128k.Q4_K_M.gguf
- Parameters: 8B
- Download: https://huggingbay.xyz/artifact/hf-model-quantfactory-granite-8b-code-instruct-128k-gguf/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-8b-code-instruct-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-8b-code-instruct-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: 169
- Stars: 3
- Card completeness: 96%

## Description

External Hugging Face catalog record for QuantFactory/granite-8b-code-instruct-128k-GGUF. Task: text generation. Library: transformers. Datasets referenced by card metadata: bigcode/commitpackft, TIGER-Lab/MathInstruct, meta-math/MetaMathQA, glaiveai/glaive-code-assistant-v3, glaive-function-calling-v2, bugdaryan/sql-create-context-instruction. Includes 9 model-card evaluation signals. Popularity signal at import: 266 downloads and 3 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Referenced datasets: bigcode/commitpackft, TIGER-Lab/MathInstruct, meta-math/MetaMathQA, glaiveai/glaive-code-assistant-v3, glaive-function-calling-v2, bugdaryan/sql-create-context-instruction, garage-bAInd/Open-Platypus, nvidia/HelpSteer
- Metrics: code_eval
- Paper ids: 2407.13739
- Model-index entries: granite-8B-Code-instruct-128k
- Evaluation signals: 9 model-card eval results
- File hints: 16 upstream file samples

## Evaluation Signals

- HumanEvalSynthesis (Python): pass@1 = 62.2 (text-generation)
- HumanEvalSynthesis (Average): pass@1 = 51.4 (text-generation)
- HumanEvalExplain (Average): pass@1 = 38.9 (text-generation)
- HumanEvalFix (Average): pass@1 = 38.3 (text-generation)
- RepoQA (Python@16K): pass@1 (thresh=0.5) = 73 (text-generation)
- RepoQA (C++@16K): pass@1 (thresh=0.5) = 37 (text-generation)
- RepoQA (Java@16K): pass@1 (thresh=0.5) = 73 (text-generation)
- RepoQA (TypeScript@16K): pass@1 (thresh=0.5) = 62 (text-generation)
- RepoQA (Rust@16K): pass@1 (thresh=0.5) = 63 (text-generation)

## Referenced Data

- Dataset: bigcode/commitpackft
- Dataset: TIGER-Lab/MathInstruct
- Dataset: meta-math/MetaMathQA
- Dataset: glaiveai/glaive-code-assistant-v3
- Dataset: glaive-function-calling-v2
- Dataset: bugdaryan/sql-create-context-instruction
- Dataset: garage-bAInd/Open-Platypus
- Dataset: nvidia/HelpSteer
- Dataset: bigcode/self-oss-instruct-sc2-exec-filter-50k
- Paper: 2407.13739

## File Hints

- .gitattributes (2.5 KB)
- README.md (7.6 KB)
- granite-8b-code-instruct-128k.Q2_K.gguf (2.9 GB) LFS
- granite-8b-code-instruct-128k.Q3_K_L.gguf (4.0 GB) LFS
- granite-8b-code-instruct-128k.Q3_K_M.gguf (3.7 GB) LFS
- granite-8b-code-instruct-128k.Q3_K_S.gguf (3.3 GB) LFS
- granite-8b-code-instruct-128k.Q4_0.gguf (4.3 GB) LFS
- granite-8b-code-instruct-128k.Q4_1.gguf (4.7 GB) LFS
- granite-8b-code-instruct-128k.Q4_K_M.gguf (4.5 GB) LFS
- granite-8b-code-instruct-128k.Q4_K_S.gguf (4.3 GB) LFS
- granite-8b-code-instruct-128k.Q5_0.gguf (5.2 GB) LFS
- granite-8b-code-instruct-128k.Q5_1.gguf (5.6 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 2026-08-28T09:50:39.259Z.
- Open license detected as apache-2.0.
- Model-index metadata found for granite-8B-Code-instruct-128k.
- Model card references dataset context: bigcode/commitpackft, TIGER-Lab/MathInstruct, meta-math/MetaMathQA, glaiveai/glaive-code-assistant-v3.
- 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-8b-code-instruct-128k-gguf
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-8b-code-instruct-128k-gguf/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-8b-code-instruct-128k-gguf/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-8b-code-instruct-128k-gguf/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-quantfactory-granite-8b-code-instruct-128k-gguf
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-8b-code-instruct-128k-gguf/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-quantfactory-granite-8b-code-instruct-128k-gguf&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-granite-8b-code-instruct-128k-gguf/decentralized-fallbacks