alt.freeweights.qwen / Qwen3-32B-SweSmith-20step

From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-32B-SweSmith-20step

Date: 2026-11-15Commit: b879f48Signed: 2DC28CC7B26A283B ✓

Text generation model with 32.8B parameters. Safetensors weights, 65.5 GB in all. Published by laion under Apache-2.0.

32.8B params65.5GBQwen3-32B-SweSmith-20stepsafetensorspermissive

FactsParams32.8BSize65.5 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get laion/Qwen3-32B-SweSmith-20step
# manifest sha256 5ceedffe59d7… · 65.5 GB · 25 files
$ fw verify ./Qwen3-32B-SweSmith-20step laion/Qwen3-32B-SweSmith-20step

From sourceHosted (signed)laion/Qwen3-32B-SweSmith-20stepLast check: 2026-11-15 04:29 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Qwen3-32B.

Works with

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 65.5 GB
Weights: 65.5 GB (safetensors)
Parameters: 32.8B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 25, each with a sha256
Publisher: laion
Added: 2026-11-15
Section: alt.freeweights.qwen

Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-32B

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 04:29 UTC	passed

Model card

From the publisher at commit b879f48. Shown as plain text with links; images open at the publisher.

Qwen3-32B-SweSmith-20step#

RL-trained Qwen3-32B on SWEsmith.

Training Details#

Base model: Qwen/Qwen3-32B
Training method: rloo_n
Training data: 2,500 SWEsmith tasks
Steps: 20 global steps
Infrastructure: 16x4 GH200 GPU nodes (GCP), FSDP2 with TP=2 for inference engines (24 inference engines + 4 policy/ref nodes)
Sandbox environment: Beta9/Beam containers for code execution

Training Curve#

Metric	Step 1	Step 10	Step 20
Avg Raw Reward	0.031	0.041	0.072
Pass@8	0.141	0.156	0.234

Files

25 files · 65.5 GBWeights 65.5 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 25 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	912 B	3e07b5b72ded1a31cdbcd1b8ec9d83751ff0d7d89b265a19a97644da8b8519fc
added_tokens.json	707 B	c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja	4.17 KB	a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json	2.27 KB	e76b96d0b312e0e8752014833e92605c730fdf8c2ac87b8a4d8bf9f6fed458f7
generation_config.json	214 B	19d9395705449004ddebeeaf62841338a48cc8df85cddb1ca0b2c60396d95c96
merges.txt	1.67 MB	8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00013.safetensors	5.32 GB	8fed77355b82f1a9348ff46cc28bd831b3266e374e72d1068923f8eeae092c02
model-00002-of-00013.safetensors	5.14 GB	73091b1733b208864d345343c3985612d60fd432969300becd1dead0fdea816c
model-00003-of-00013.safetensors	5.33 GB	bbfb5905783303e2acc50854d9b5f689ffc08d1f3559675ff23622737299c6e7
model-00004-of-00013.safetensors	5.14 GB	9f76662945cdfaf4e0bc70e58ddab1609d9480440a55aa72bbd16c5588d0ff99
model-00005-of-00013.safetensors	5.14 GB	59630fcb700384d50d38a7b001e679d00978684bebb0a17ebbe6afe922fb133a
model-00006-of-00013.safetensors	5.33 GB	28d6e850a696ccc75884f6e7a7a097444555f37c251841cb8810962c177451ec
model-00007-of-00013.safetensors	5.14 GB	86e67076223edec1f73e8aa87ed1efa5293b0730841157e7303ae37fde1d1cc3
model-00008-of-00013.safetensors	5.14 GB	ccc492f1517df3c8279359341888cf24473079cef68267fefe0102d2860ed5f8
model-00009-of-00013.safetensors	5.33 GB	de5d11827f605bfe36566305bf959557c24ea196349542bd193edd02615d4ff6
model-00010-of-00013.safetensors	5.14 GB	95f2c6b715a817266908fb9ea223cbf0a0f23b0d5be27a2e8c860daecf737b96
model-00011-of-00013.safetensors	5.14 GB	e644630c922444a21a5b39f3c1951f1448204fbc70b0ab369d91c1e40e5a0c29
model-00012-of-00013.safetensors	5.33 GB	6099bee2f3404f46dacd34b72094821d6d04d0a43551af06bfa68508fa7913f2
model-00013-of-00013.safetensors	2.93 GB	d9b21616cfee5d0157131d19a22f1757b3c5c5e0ebf1820d0bb59d0cfbd53a64
model.safetensors.index.json	58.3 KB	046cb77526bba0b2b7ebdf21aa2a5796653675a98a2b268b79271c760b030c7b
special_tokens_map.json	613 B	76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json	11.4 MB	aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json	5.40 KB	443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0
vocab.json	2.78 MB	ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
b879f48867 pinned now	2026-11-15 04:29 UTC	25 files · 65.5 GB

Use it

$ fw get laion/Qwen3-32B-SweSmith-20step
# manifest sha256 5ceedffe59d7… · 65.5 GB · 25 files
$ fw verify ./Qwen3-32B-SweSmith-20step laion/Qwen3-32B-SweSmith-20step

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/Qwen3-32B-SweSmith-20step.json --dir ./Qwen3-32B-SweSmith-20step
$ python3 fw.py verify ./Qwen3-32B-SweSmith-20step ./laion__Qwen3-32B-SweSmith-20step.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/Qwen3-32B-SweSmith-20step --revision b879f48867a257ce50b287d92f0997d39cf4488b --local-dir ./Qwen3-32B-SweSmith-20step

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("laion/Qwen3-32B-SweSmith-20step", revision="b879f48867a257ce50b287d92f0997d39cf4488b")
model = AutoModelForCausalLM.from_pretrained("laion/Qwen3-32B-SweSmith-20step", revision="b879f48867a257ce50b287d92f0997d39cf4488b", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/Qwen3-32B-SweSmith-20step --revision b879f48867a257ce50b287d92f0997d39cf4488b

Run at home

License

Name: Apache License 2.0
Id: Apache-2.0
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: License as declared by the publisher. No person read it. 2026-11-15
Text in: README.md
Text sha256: 3e07b5b72ded1a31cdbcd1b8ec9d83751ff0d7d89b265a19a97644da8b8519fc
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.qwenSubject: Qwen3-32B-SweSmith-20stepDate: 2026-11-15Commit: b879f48Signed: 2DC28CC7B26A283B ✓

Upstream: laion/Qwen3-32B-SweSmith-20step
Pinned commit: b879f48867a257ce50b287d92f0997d39cf4488b
Manifest: Qwen3-32B-SweSmith-20step.json · .minisig
Manifest sha256: 5ceedffe59d7aeaafa9aa60e790b520bfc1b6bdc135e097b5a106eee8fabdfa0
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:29 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/Qwen3-32B-SweSmith-20step.json
$ curl -O https://freeweights.allternit.com/manifests/laion/Qwen3-32B-SweSmith-20step.json.minisig
$ minisign -Vm Qwen3-32B-SweSmith-20step.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen3-32B · this model is a finetune of it

No model in the catalog names this one as its parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/Qwen3-32B-SweSmith-20step

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. Qwen3-32B-SweSmith-20step.json. Provenance. Takedown history: none.

Source

huggingface.co/laion/Qwen3-32B-SweSmith-20step

Related models

All of alt.freeweights.qwen →

From:

BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen

From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1

From:

BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923

From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct

From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA

From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF

Qwen3-32B-SweSmith-20step

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

Qwen3-32B-SweSmith-20step#

Training Details#

Training Curve#

Files

Use it

License

Provenance

How to verify

Model tree

Related models