CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.8-3.6-27B-blend
From: JetBrains <huggingface.co/JetBrains>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.8-3.6-27B-blend

Date: 2026-11-15Commit: 172ea6eSigned: 2DC28CC7B26A283B ✓

Image text to text model with 27.8B parameters. Safetensors weights, 59.4 GB in all. Published by JetBrains under Apache-2.0.

27.8B params59.4GBQwen3.8-3.6-27B-blendsafetensorspermissive
FactsParams27.8BSize59.4 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get JetBrains/Qwen3.8-3.6-27B-blend
# manifest sha256 62331ce3bf5d… · 59.4 GB · 37 files
$ fw verify ./Qwen3.8-3.6-27B-blend JetBrains/Qwen3.8-3.6-27B-blend
From sourceHosted (signed)JetBrains/Qwen3.8-3.6-27B-blendLast check: 2026-11-15 03:43 UTC
Run at homeGet help

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

Merge of Qwen3.6-27B.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
59.4 GB
Weights
59.4 GB (safetensors)
Parameters
27.8B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
37, each with a sha256
Publisher
JetBrains
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.6-27B

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 03:43 UTCpassed

Model card

From the publisher at commit 172ea6e. Shown as plain text with links; images open at the publisher.

Qwen3.8-3.6-27B-blend#

Unofficial JetBrains derivative. This model was prepared by JetBrains using Qwen models developed by Alibaba Cloud. This release is not affiliated with, sponsored by, or endorsed by Alibaba Cloud or Alibaba Group.

Coding quality versus output tokens: tasks completed on JetBrains’ 100-task internal coding benchmark

Tasks completed versus output tokens on JetBrains’ 100-task internal coding benchmark. Reasoning settings differ between configurations; see the article for methodology and context.

Read Making Local AI Smarter and Faster for the Junie Local release story, coding evaluations, token-efficiency results, and MTP runtime experiments.

Available formats: BF16 · GGUF · MLX 4-bit · MTP MLX 4-bit · DFlash2 drafter.

This model is a 50/50 combination of Qwen3.6-27B and Qwen3.8-27B, created by linearly interpolating their checkpoint parameters. The configuration, tokenizer, processor, and chat template are retained from Qwen3.8-27B. Exact source revisions and merge settings are recorded in merge-manifest.json.

The interpolation uses float32 accumulation.

0.5 * Qwen/Qwen3.6-27B + 0.5 * Qwen/Qwen3.8-27B
  • Qwen/Qwen3.6-27B revision 6a9e13bd6fc8f0983b9b99948120bc37f49c13e9
  • Qwen/Qwen3.8-27B revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0

DFlash2 draft model#

This repository bundles a DFlash2 draft model for this blend under DFlash2/ — the same weights as JetBrains/Qwen3.8-3.6-27B-blend-DFlash2, fine-tuned from the public Qwen 3.8 DFlash2 drafter on Junie coding trajectories. DFlash2/ is a standalone draft checkpoint (verified by the target during speculative decoding); it is not part of the target model. See the standalone repository for documentation and serving examples.

License and attribution#

Distributed under the Apache License, Version 2.0. The original Qwen LICENSE, including Copyright 2026 Alibaba Cloud, is retained unchanged.

Copyright © 2026 JetBrains s.r.o. This notice applies only to original material contributed by JetBrains. Upstream Qwen material remains subject to its original copyright and attribution notices.

See NOTICE for attribution and CHANGES.md for a description of the modifications and the affected files.

Note on acceptable use#

This model is distributed under the Apache License, Version 2.0. This notice does not modify the License. Users are reminded that using this model, or its outputs, to infringe the copyright or other intellectual property rights of third parties may violate applicable law, independent of the terms of this License.

Training and upstream information#

No additional training or fine-tuning was performed, and no additional training data was used to create this derivative; its preparation consisted of the checkpoint merge and, where applicable, the extraction, format conversion, and quantization described above and in CHANGES.md.

For upstream information, see the official Qwen3.6-27B model card and Qwen3.8-27B model card. Qwen also publishes a Training Data Summary, which describes training data for models powering qwen.ai generally; it does not identify the exact training datasets for these two checkpoints.

Files

37 files · 59.4 GBWeights 59.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 37 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
CHANGES.md4.34 KBbba59d2ae37cb665783b2f8db25e027e7ab5d3ac88550d9bcbee31144807e46e
DFlash2/README.md1.02 KB3c8fe1149837245e4173ad117cc51c8dcf2f0f35a2c6fb903a4ef5242784665b
DFlash2/config.json1.29 KB3f90bdee5b0de39ad1034b504171ac87a52b50144996b43dc70bb3ff9298feb2
DFlash2/model.safetensors3.85 GBfbee4cc4790035d0a4d4d7cece25f41a0f8d629b4c630d19be86a994ee90a477
LICENSE11.5 KBbbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a
NOTICE776 B03776b100c632d38529ecebc16b1057720118f500c472f347666f6668b379fe7
README.md4.26 KB33408bdbf96df3edeeed51ff66716c0be95464a38dee22ec16ec6aefdf865c06
chat_template.jinja8.95 KBc3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041
config.json4.31 KB191e0af232104ed8b65258cf3fb2b842e288008baca7633c11b82a1ac7203aab
generation_config.json202 Be70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e
merge-manifest.json959 B57767a54ab55df5b0e033cc6880726e5352cfea265bac461904bcfb2a8b69336
merges.txt3.35 MBa9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model-00001-of-00018.safetensors3.97 GB5dcc8a33f79a5e063f8648c139f4f7eb14acbd53c44226776af8287ed23291e7
model-00002-of-00018.safetensors3.04 GB8a308f482a8bbd87d4bdd8d627aa0c50d30e07a165f835d256aadb40f3ea33d4
model-00003-of-00018.safetensors2.54 GBd35724d2fd43fa933e049d3075341694cc1c445c506f91fb88122ee5cd017f84
model-00004-of-00018.safetensors3.99 GB673f15b2b35d050c0085c698bd334d59a6e3e780444bafff2355b768f447d265
model-00005-of-00018.safetensors2.10 GB7623ad5b8d4c9bcb784fc8dc268dfb518a14b132b7bb064f8c0f9acdfd076c80
model-00006-of-00018.safetensors3.98 GB2d46dc60da2269dc308a4f21cf944a625a87e0ecb0d4aa26f346ab52f0c9f65e
model-00007-of-00018.safetensors2.11 GB934883a996ed41778fe56d5afa0a533df6508d2b627c54b6ef2e39870827ed14
model-00008-of-00018.safetensors3.98 GB7bfae1bf1254971178c9ecf2d9fcabc0998578ca6c64022b662404c21a4f5e26
model-00009-of-00018.safetensors2.11 GBf0bf6b75c951e190cb60980124e59c7c050b0d69c6b07ffb828318e69ddb0dce
model-00010-of-00018.safetensors3.98 GB37353451306ed0aaba5b2d7ce7fca000fe0db9426ed5ffdd7f51c88b75ab6138
model-00011-of-00018.safetensors2.11 GB8d7f6535a8c3bd6ae19051fdbaf087a933a435655425a4a281ce1bb71557ba5b
model-00012-of-00018.safetensors3.98 GBf52f6f39ef26d09e1917ecd1c0ff75d9b6f1958593efd913c530e756449a9ffd
model-00013-of-00018.safetensors2.11 GBd73e22a85ec5ad13c59903ae15f1815202fe11f5cb58f11f4463b5defc6629db
model-00014-of-00018.safetensors3.98 GBc3c7847f227e7cfd8021241e874efff1fc5f219de32cf16818495c6e230da11f
model-00015-of-00018.safetensors2.11 GB1187f2cc10d9f86f77f2ef162fab80eeab446645d6d60556a0d05d0821d5244c
model-00016-of-00018.safetensors3.98 GB9b221bc8f0b5b908c195f8d74ac4fbbe729947b8f9ea2a5172c8bbeb203e28d7
model-00017-of-00018.safetensors2.11 GBbb4d9b0ab787fec853d49c1bc7cfc68c99eba02a8805f73c756e2b43afb3bdb8
model-00018-of-00018.safetensors3.39 GB181f41305054e557806eb7755bfe9261dfe4eefb3e78cb803bd8c978024b3fe5
model.safetensors.index.json112 KB77042094076611b69791a610065f28b7013b8c621795fa86ddccc8bac7d1b9df
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
tokenizer.json12.8 MB0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
tokenizer_config.json17.9 KBb11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27
video_preprocessor_config.json385 B7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
172ea6ea91 pinned now2026-11-15 03:43 UTC37 files · 59.4 GB

Use it

$ fw get JetBrains/Qwen3.8-3.6-27B-blend
# manifest sha256 62331ce3bf5d… · 59.4 GB · 37 files
$ fw verify ./Qwen3.8-3.6-27B-blend JetBrains/Qwen3.8-3.6-27B-blend
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/JetBrains/Qwen3.8-3.6-27B-blend.json --dir ./Qwen3.8-3.6-27B-blend $ python3 fw.py verify ./Qwen3.8-3.6-27B-blend ./JetBrains__Qwen3.8-3.6-27B-blend.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download JetBrains/Qwen3.8-3.6-27B-blend --revision 172ea6ea91b8310a11a96d88fa57766b03233ab5 --local-dir ./Qwen3.8-3.6-27B-blend
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("JetBrains/Qwen3.8-3.6-27B-blend", revision="172ea6ea91b8310a11a96d88fa57766b03233ab5") model = AutoModelForImageTextToText.from_pretrained("JetBrains/Qwen3.8-3.6-27B-blend", revision="172ea6ea91b8310a11a96d88fa57766b03233ab5", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve JetBrains/Qwen3.8-3.6-27B-blend --revision 172ea6ea91b8310a11a96d88fa57766b03233ab5
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
LICENSE
Text sha256
bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a
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: JetBrains <huggingface.co/JetBrains>Newsgroups: alt.freeweights.qwenSubject: Qwen3.8-3.6-27B-blendDate: 2026-11-15Commit: 172ea6eSigned: 2DC28CC7B26A283B ✓
Upstream
JetBrains/Qwen3.8-3.6-27B-blend
Pinned commit
172ea6ea91b8310a11a96d88fa57766b03233ab5
Manifest
Qwen3.8-3.6-27B-blend.json · .minisig
Manifest sha256
62331ce3bf5d1a4b375ad7c0e66ba696f34de42f17af1634fef7218dcfa99ac6
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:43 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/JetBrains/Qwen3.8-3.6-27B-blend.json $ curl -O https://freeweights.allternit.com/manifests/JetBrains/Qwen3.8-3.6-27B-blend.json.minisig $ minisign -Vm Qwen3.8-3.6-27B-blend.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/Qwen3.6-27B · this model is a merge of it

1 model in the catalog name this one as their parent.

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download JetBrains/Qwen3.8-3.6-27B-blend
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.8-3.6-27B-blend.json. Provenance. Takedown history: none.
Source
huggingface.co/JetBrains/Qwen3.8-3.6-27B-blend

Variants

1 quantized or adapter build of Qwen3.8-3.6-27B-blend. Each has its own license check and page.

SubjectSizeParamsLicenseDate
JetBrains-Qwen3.8-3.6-27B-blend-GGUFHosted (signed) From: bartowski in alt.freeweights.qwen447 GB—Permissive2026-11-15

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