# tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4

Model from Hugging Face for text generation: tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4 · transformers

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4/blob/main/LICENSE)
- Source: https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4
- Hosting: hosted (15 files)
- Files: 15 hosted of 28 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: 15 files, 19.3 GB
- Full repo upstream: 19.3 GB
- Recommended file: 19.3 GB (5 files)
- Parameters: 32B
- Download: https://huggingbay.xyz/artifact/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/download-plan)
- Per-file SHA-256: available for 15 of 15 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/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: 493
- Stars: 2
- Card completeness: 96%

## Description

External Hugging Face catalog record for tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4. Task: text generation. Library: transformers. Languages: en, ja. Datasets referenced by card metadata: tokyotech-llm/swallow-math-v2, tokyotech-llm/swallow-code-v2, tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1, tokyotech-llm/lmsys-chat-1m-synth. Popularity signal at import: 75,326 downloads and 2 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Languages: en, ja
- Referenced datasets: tokyotech-llm/swallow-math-v2, tokyotech-llm/swallow-code-v2, tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1, tokyotech-llm/lmsys-chat-1m-synth
- Paper ids: 2505.09388, 2404.17733, 2412.02595
- File hints: 16 upstream file samples

## Referenced Data

- Dataset: tokyotech-llm/swallow-math-v2
- Dataset: tokyotech-llm/swallow-code-v2
- Dataset: tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1
- Dataset: tokyotech-llm/lmsys-chat-1m-synth
- Paper: 2505.09388
- Paper: 2404.17733
- Paper: 2412.02595

## File Hints

- .gitattributes (1.6 KB)
- LICENSE (11 KB)
- README.md (11 KB)
- added_tokens.json (707 B)
- chat_template.jinja (4.1 KB)
- config.json (3.3 KB)
- figure/qwen3-swallow-32b-rl_en_en.svg (84 KB)
- figure/qwen3-swallow-32b-rl_en_ja.svg (84 KB)
- figure/qwen3-swallow-32b-rl_ja_en.svg (92 KB)
- figure/qwen3-swallow-32b-rl_ja_ja.svg (92 KB)
- figure/qwen3-swallow-32b-series_en_en.svg (83 KB)
- figure/qwen3-swallow-32b-series_en_ja.svg (83 KB)

## 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 2026-09-21T06:20:46.584Z.
- Upstream license: apache-2.0. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model card references dataset context: tokyotech-llm/swallow-math-v2, tokyotech-llm/swallow-code-v2, tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1, tokyotech-llm/lmsys-chat-1m-synth.
- 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-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-tokyotech-llm-qwen3-swallow-32b-rl-v0-2-awq-int4/decentralized-fallbacks