# bartowski/granite-20b-code-instruct-GGUF

Model from Hugging Face for text generation: bartowski/granite-20b-code-instruct-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/bartowski/granite-20b-code-instruct-GGUF
- Hosting: unknown (no download location recorded)
- Files: 38 listed, none hosted here
- 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: availability unknown
- Full repo upstream: 454.1 GB
- Recommended file: 12.8 GB (Q4_K_M) · granite-20b-code-instruct-Q4_K_M.gguf
- Parameters: 20B
- Download: none recorded
- Per-file SHA-256: not available (no files hosted on Hugging Bay)
- 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: 2444
- Stars: 7
- Card completeness: 96%

## Description

External Hugging Face catalog record for bartowski/granite-20b-code-instruct-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. Base model: ibm-granite/granite-20b-code-instruct. Includes 8 model-card evaluation signals. Popularity signal at import: 10,904 downloads and 7 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Base model: ibm-granite/granite-20b-code-instruct
- 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
- Model-index entries: granite-20b-code-instruct
- Evaluation signals: 7 model-card eval results
- File hints: 16 upstream file samples

## Evaluation Signals

- HumanEvalSynthesis(Python): pass@1 = 60.4 (text-generation)
- HumanEvalSynthesis(Python): pass@1 = 53.7 (text-generation)
- HumanEvalSynthesis(Python): pass@1 = 58.5 (text-generation)
- HumanEvalSynthesis(Python): pass@1 = 42.1 (text-generation)
- HumanEvalSynthesis(Python): pass@1 = 45.7 (text-generation)
- HumanEvalSynthesis(Python): pass@1 = 42.7 (text-generation)
- HumanEvalSynthesis(Python): pass@1 = 44.5 (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

## File Hints

- .gitattributes (4.2 KB)
- README.md (12 KB)
- granite-20b-code-instruct-IQ1_M.gguf (4.6 GB) LFS
- granite-20b-code-instruct-IQ1_S.gguf (4.2 GB) LFS
- granite-20b-code-instruct-IQ2_M.gguf (6.6 GB) LFS
- granite-20b-code-instruct-IQ2_S.gguf (6.1 GB) LFS
- granite-20b-code-instruct-IQ2_XS.gguf (5.7 GB) LFS
- granite-20b-code-instruct-IQ2_XXS.gguf (5.2 GB) LFS
- granite-20b-code-instruct-IQ3_M.gguf (8.9 GB) LFS
- granite-20b-code-instruct-IQ3_S.gguf (8.3 GB) LFS
- granite-20b-code-instruct-IQ3_XS.gguf (8.1 GB) LFS
- granite-20b-code-instruct-IQ3_XXS.gguf (7.5 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 2026-09-18T19:18:02.295Z.
- Upstream license: apache-2.0. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model-index metadata found for granite-20b-code-instruct.
- Model card references dataset context: bigcode/commitpackft, TIGER-Lab/MathInstruct, meta-math/MetaMathQA, glaiveai/glaive-code-assistant-v3.
- Not locally hosted, mirrored, signed, or rescanned by Hugging Bay.
- 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-bartowski-granite-20b-code-instruct-gguf
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-bartowski-granite-20b-code-instruct-gguf/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-bartowski-granite-20b-code-instruct-gguf/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-bartowski-granite-20b-code-instruct-gguf/distribution
- Manifest: not available until files are hosted and release checks pass.
- Request mirror: POST https://huggingbay.xyz/api/artifacts/hf-model-bartowski-granite-20b-code-instruct-gguf/mirror-request
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-bartowski-granite-20b-code-instruct-gguf/decentralized-fallbacks