CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / DeepSWE-Preview-GGUF
From: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.textSubject:

DeepSWE-Preview-GGUF

Date: 2026-11-15Commit: 41965f8Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 98.8 GB in all. Published by lmstudio-community under MIT.

text98.8GBDeepSWE-Preview-GGUFggufpermissive
FactsParamsnot statedSize98.8 GBFormatsggufTasktext generationLicenseMITFrom sourcepermissive
$ fw get lmstudio-community/DeepSWE-Preview-GGUF
# manifest sha256 a0f92307ae66… · 98.8 GB · 6 files
$ fw verify ./DeepSWE-Preview-GGUF lmstudio-community/DeepSWE-Preview-GGUF
From sourceHosted (signed)lmstudio-community/DeepSWE-Preview-GGUFLast check: 2026-11-15 05:24 UTC
Run at homeGet help

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

Quantized of DeepSWE-Preview.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
98.8 GB
Weights
17.3 GB (smallest of 4 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
MIT (permissive)
Files
6, each with a sha256
Publisher
lmstudio-community
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: agentica-org/DeepSWE-Preview

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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:24 UTCpassed

Model card

From the publisher at commit 41965f8. Shown as plain text with links; images open at the publisher.

💫 Community Model> DeepSWE Preview by Agentica-Org#

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Model creator: agentica-org

Original model: DeepSWE-Preview

GGUF quantization: provided by bartowski based on llama.cpp release b5760

Technical Details#

Supports a context length of 40k tokens

Trained on top of Qwen3-32B with thinking mode enabled

Coding agent trained with only reinforcement learning (RL) to excel at software engineering (SWE) tasks

Achieves an impressive 59.0% on SWE-Bench-Verified, which is currently #1 in the open-weights category

More details in their technical blog post

Special thanks#

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

Disclaimers#

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Files

6 files · 98.8 GBWeights 17.3 GB (smallest of 4 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 6 files with their sha256
FileSizesha256
.gitattributes1.77 KBf0450828cc36ce88d5a296e4ca6e50de39519d0ca890dbe7a4b9c5781e00ecde
DeepSWE-Preview-Q3_K_L.gguf17.3 GB17525207a0ce3258551180ef6d557d3324e834e194c75a900855669af66c3088
DeepSWE-Preview-Q4_K_M.gguf19.8 GBfb7a44a0b4fb9e4d59947d01aba39e068685b8f328e9a8bb90eb42e1164b5cf4
DeepSWE-Preview-Q6_K.gguf26.9 GBe92c8f4c985024a5dc9dade06783524d86bc284c60c9a8f5ec4b77c5734c5ba4
DeepSWE-Preview-Q8_0.gguf34.8 GBfae242fab456a9dff0332616278627881a66584058d36279e39eacd1e7997d3e
README.md2.81 KB1d16211003e98587a1ec607a433e785a7f31765e5804099f5c0fe8f74d4879eb
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
41965f82b3 pinned now2026-11-15 05:24 UTC6 files · 98.8 GB

Use it

$ fw get lmstudio-community/DeepSWE-Preview-GGUF
# manifest sha256 a0f92307ae66… · 98.8 GB · 6 files
$ fw verify ./DeepSWE-Preview-GGUF lmstudio-community/DeepSWE-Preview-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/lmstudio-community/DeepSWE-Preview-GGUF.json --dir ./DeepSWE-Preview-GGUF $ python3 fw.py verify ./DeepSWE-Preview-GGUF ./lmstudio-community__DeepSWE-Preview-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/DeepSWE-Preview-GGUF --revision 41965f82b3bcda1d90804136e01bee868ec00b45 --local-dir ./DeepSWE-Preview-GGUF
llama.cppDownload one GGUF variant (DeepSWE-Preview-Q3_K_L, 17.3 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/DeepSWE-Preview-GGUF --include "DeepSWE-Preview-Q3_K_L*" --local-dir ./DeepSWE-Preview-GGUF $ llama-server -m ./DeepSWE-Preview-GGUF/DeepSWE-Preview-Q3_K_L.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./DeepSWE-Preview-GGUF/DeepSWE-Preview-Q3_K_L.gguf\n' > Modelfile $ ollama create deepswe-preview-gguf -f Modelfile
Run at home

License

Name
MIT License
Id
MIT
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
1d16211003e98587a1ec607a433e785a7f31765e5804099f5c0fe8f74d4879eb
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: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.textSubject: DeepSWE-Preview-GGUFDate: 2026-11-15Commit: 41965f8Signed: 2DC28CC7B26A283B ✓
Upstream
lmstudio-community/DeepSWE-Preview-GGUF
Pinned commit
41965f82b3bcda1d90804136e01bee868ec00b45
Manifest
DeepSWE-Preview-GGUF.json · .minisig
Manifest sha256
a0f92307ae66b9f3c54ad0de8a81005cf7fae4bf93e0992eaff8f6f291009986
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:24 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/DeepSWE-Preview-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/DeepSWE-Preview-GGUF.json.minisig $ minisign -Vm DeepSWE-Preview-GGUF.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

agentica-org/DeepSWE-Preview · this model is a quantization of it

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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/DeepSWE-Preview-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSWE-Preview-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/lmstudio-community/DeepSWE-Preview-GGUF

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B