# QuantFactory/Baldur-8B-GGUF

Model from Hugging Face for llm: QuantFactory/Baldur-8B-GGUF · unknown

## Facts

- Type: LLM
- Task: general
- Framework: unknown
- License: agpl-3.0 — Commercial use is permitted with obligations: GPL-3.0: derivative works must be distributed under GPL-3.0 (strong copyleft). (https://spdx.org/licenses/AGPL-3.0.html)
- Source: https://huggingface.co/QuantFactory/Baldur-8B-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, 4.92 GB
- Full repo upstream: 72.7 GB
- Recommended file: 4.92 GB (Q4_K_M) · Baldur-8B.Q4_K_M.gguf
- Parameters: 8B
- Download: https://huggingbay.xyz/artifact/hf-model-quantfactory-baldur-8b-gguf/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-baldur-8b-gguf/download-plan)
- Per-file SHA-256: available for 1 of 1 hosted file via https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-baldur-8b-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: 872
- Stars: 4
- Card completeness: 96%

## Description

External Hugging Face catalog record for QuantFactory/Baldur-8B-GGUF. Library: unknown. Languages: en. Datasets referenced by card metadata: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned, Nitral-AI/Cybersecurity-ShareGPT, Nitral-AI/Medical_Instruct-ShareGPT, Nitral-AI/Olympiad_Math-ShareGPT, anthracite-org/kalo_opus_misc_240827, NewEden/Claude-Instruct-5k. Includes 6 model-card evaluation signals. Popularity signal at import: 872 downloads and 4 likes.

## Model Card Facts

- Declared license: agpl-3.0
- Pipeline: general
- Library: unknown
- Task categories: general
- Languages: en
- Referenced datasets: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned, Nitral-AI/Cybersecurity-ShareGPT, Nitral-AI/Medical_Instruct-ShareGPT, Nitral-AI/Olympiad_Math-ShareGPT, anthracite-org/kalo_opus_misc_240827, NewEden/Claude-Instruct-5k, lodrick-the-lafted/kalo-opus-instruct-3k-filtered, anthracite-org/kalo-opus-instruct-22k-no-refusal
- Model-index entries: Baldur-8B
- Evaluation signals: 6 model-card eval results
- File hints: 16 upstream file samples

## Evaluation Signals

- IFEval (0-Shot): strict accuracy = 47.82 (Text Generation)
- BBH (3-Shot): normalized accuracy = 32.54 (Text Generation)
- MATH Lvl 5 (4-Shot): exact match = 12.61 (Text Generation)
- GPQA (0-shot): acc_norm = 6.94 (Text Generation)
- MuSR (0-shot): acc_norm = 14.01 (Text Generation)
- MMLU-PRO (5-shot): accuracy = 29.49 (Text Generation)

## Referenced Data

- Dataset: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
- Dataset: Nitral-AI/Cybersecurity-ShareGPT
- Dataset: Nitral-AI/Medical_Instruct-ShareGPT
- Dataset: Nitral-AI/Olympiad_Math-ShareGPT
- Dataset: anthracite-org/kalo_opus_misc_240827
- Dataset: NewEden/Claude-Instruct-5k
- Dataset: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
- Dataset: anthracite-org/kalo-opus-instruct-22k-no-refusal
- Dataset: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
- Dataset: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
- Dataset: anthracite-org/kalo_misc_part2
- Dataset: Nitral-AI/Creative_Writing-ShareGPT

## File Hints

- .gitattributes (2.3 KB)
- Baldur-8B.Q2_K.gguf (3.0 GB) LFS
- Baldur-8B.Q3_K_L.gguf (4.0 GB) LFS
- Baldur-8B.Q3_K_M.gguf (3.7 GB) LFS
- Baldur-8B.Q3_K_S.gguf (3.4 GB) LFS
- Baldur-8B.Q4_0.gguf (4.3 GB) LFS
- Baldur-8B.Q4_1.gguf (4.8 GB) LFS
- Baldur-8B.Q4_K_M.gguf (4.6 GB) LFS
- Baldur-8B.Q4_K_S.gguf (4.4 GB) LFS
- Baldur-8B.Q5_0.gguf (5.2 GB) LFS
- Baldur-8B.Q5_1.gguf (5.7 GB) LFS
- Baldur-8B.Q5_K_M.gguf (5.3 GB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: review
- 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 2026-09-18T02:01:42.618Z.
- Upstream license: agpl-3.0. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model-index metadata found for Baldur-8B.
- Model card references dataset context: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned, Nitral-AI/Cybersecurity-ShareGPT, Nitral-AI/Medical_Instruct-ShareGPT, Nitral-AI/Olympiad_Math-ShareGPT.
- 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-baldur-8b-gguf
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-baldur-8b-gguf/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-baldur-8b-gguf/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-baldur-8b-gguf/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-quantfactory-baldur-8b-gguf
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-baldur-8b-gguf/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-quantfactory-baldur-8b-gguf&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-baldur-8b-gguf/decentralized-fallbacks