# unsloth/Qwen3-8B-GGUF

This model is a causal language model with 8.2B parameters, 32 attention heads for Q and 8 for KV, and a native context length of 32,768 tokens. It can switch between thinking and non thinking modes, and the card says it supports tool calling and context lengths up to 131,072 tokens with YaRN.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-unsloth-qwen3-8b-gguf
- Citation: unsloth/Qwen3-8B-GGUF. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-unsloth-qwen3-8b-gguf (retrieved 2026-11-14).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/files?limit=100. How checks work: https://huggingbay.xyz/verification

## 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/unsloth/Qwen3-8B-GGUF
- Hosting: hosted (29 files)
- Files: 29 hosted of 31 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: 29 hosted of 31 listed
- Full repo upstream: 133.4 GB
- Recommended file: 5.03 GB (Q4_K_M) · Qwen3-8B-Q4_K_M.gguf
- Download: https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/download-plan)
- Per-file SHA-256: available for 29 of 29 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/files?limit=100
- Availability: Ready
- Downloadable: yes
- Run-ready: yes (canonical authority certifies a verified run path; see the deployment plan for exact commands)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 124199
- Stars: 136
- Card completeness: 88%

## Description

This model is a causal language model with 8.2B parameters, 32 attention heads for Q and 8 for KV, and a native context length of 32,768 tokens. It can switch between thinking and non thinking modes, and the card says it supports tool calling and context lengths up to 131,072 tokens with YaRN.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: thin
- 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 2026-06-30T01:53:18.213Z.
- Open license detected as apache-2.0.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-unsloth-qwen3-8b-gguf
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-unsloth-qwen3-8b-gguf
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-unsloth-qwen3-8b-gguf&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen3-8b-gguf/decentralized-fallbacks