alt.freeweights.qwen / Qwen3.5-27B-GPTQ-Int4

From:

Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-27B-GPTQ-Int4

Date: 2026-11-15Commit: 8f0c09fSigned: 2DC28CC7B26A283B ✓

Image text to text model with 27.8B parameters. Safetensors weights, 30.3 GB in all. Published by Qwen under Apache-2.0.

27.8B params

30.3GBQwen3.5-27B-GPTQ-Int4safetensorspermissive

FactsParams27.8BSize30.3 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive

$ fw get Qwen/Qwen3.5-27B-GPTQ-Int4
# manifest sha256 b557bece712a… · 30.3 GB · 26 files
$ fw verify ./Qwen3.5-27B-GPTQ-Int4 Qwen/Qwen3.5-27B-GPTQ-Int4

From sourceHosted (signed)Qwen/Qwen3.5-27B-GPTQ-Int4Last check: 2026-11-15 02:35 UTC

Run at home Get help

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

Works with

Run23 Fine-tune29 Convert15 Evaluate13 Scan13 Apps62

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 23

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad 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: 30.3 GB
Weights: 30.2 GB (safetensors)
Parameters: 27.8B
Formats: safetensors
Task: image text to text
License: Apache-2.0 (permissive)
Files: 26, each with a sha256
Publisher: Qwen
Added: 2026-11-15
Section: alt.freeweights.qwen

Lineage

Original release from the publisher.

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 02:35 UTC	passed

Model card

From the publisher at commit 8f0c09f. Shown as plain text with links; images open at the publisher.

Qwen3.5-27B-GPTQ-Int4#

Image: image

Qwen Chat

Note. This repository contains int4-quantized model weights and configuration files for the post-trained model in the Hugging Face Transformers format.

These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.

Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.

Qwen3.5 Highlights#

Qwen3.5 features the following enhancement:

Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.

Image: Benchmark Results

For more details, please refer to our blog post Qwen3.5.

Model Overview#

Type: Causal Language Model with Vision Encoder
Training Stage: Pre-training & Post-training
Language Model
- Number of Parameters: 27B
- Hidden Dimension: 5120
- Token Embedding: 248320 (Padded)
- Number of Layers: 64
- Hidden Layout: 16 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
- Gated DeltaNet:
  - Number of Linear Attention Heads: 48 for V and 16 for QK
  - Head Dimension: 128
- Gated Attention:
  - Number of Attention Heads: 24 for Q and 4 for KV
  - Head Dimension: 256
  - Rotary Position Embedding Dimension: 64
- Feed Forward Network:
  - Intermediate Dimension: 17408
- LM Output: 248320 (Padded)
- MTP: trained with multi-steps
Context Length: 262,144 natively and extensible up to 1,010,000 tokens.
Quantization: GPTQ 4-bit

Benchmark Results#

Language#

| Knowledge

| MMLU-Pro | 83.7 | 80.8 | 84.4 | 86.7 | 86.1 | 85.3

| MMLU-Redux | 93.7 | 91.0 | 93.8 | 94.0 | 93.2 | 93.3

| C-Eval | 82.2 | 76.2 | 92.1 | 91.9 | 90.5 | 90.2

| SuperGPQA | 58.6 | 54.6 | 64.9 | 67.1 | 65.6 | 63.4

| Instruction Following

| IFEval | 93.9 | 88.9 | 87.8 | 93.4 | 95.0 | 91.9

| IFBench | 75.4 | 69.0 | 51.7 | 76.1 | 76.5 | 70.2

| MultiChallenge | 59.0 | 45.3 | 50.2 | 61.5 | 60.8 | 60.0

| Long Context

| AA-LCR | 68.0 | 50.7 | 60.0 | 66.9 | 66.1 | 58.5

| LongBench v2 | 56.8 | 48.2 | 54.8 | 60.2 | 60.6 | 59.0

| STEM & Reasoning

| HLE w/ CoT | 19.4 | 14.9 | 18.2 | 25.3 | 24.3 | 22.4

| GPQA Diamond | 82.8 | 80.1 | 81.1 | 86.6 | 85.5 | 84.2

| HMMT Feb 25 | 89.2 | 90.0 | 85.1 | 91.4 | 92.0 | 89.0

| HMMT Nov 25 | 84.2 | 90.0 | 89.5 | 90.3 | 89.8 | 89.2

| Coding

| SWE-bench Verified | 72.0 | 62.0 | -- | 72.0 | 72.4 | 69.2

| Terminal Bench 2 | 31.9 | 18.7 | -- | 49.4 | 41.6 | 40.5

| LiveCodeBench v6 | 80.5 | 82.7 | 75.1 | 78.9 | 80.7 | 74.6

| CodeForces | 2160 | 2157 | 2146 | 2100 | 1899 | 2028

| OJBench | 40.4 | 41.5 | 32.7 | 39.5 | 40.1 | 36.0

| FullStackBench en | 30.6 | 58.9 | 61.1 | 62.6 | 60.1 | 58.1

| FullStackBench zh | 35.2 | 60.4 | 63.1 | 58.7 | 57.4 | 55.0

| General Agent

| BFCL-V4 | 55.5 | -- | 54.8 | 72.2 | 68.5 | 67.3

| TAU2-Bench | 69.8 | -- | 58.5 | 79.5 | 79.0 | 81.2

| VITA-Bench | 13.9 | -- | 31.6 | 33.6 | 41.9 | 31.9

| DeepPlanning | 17.9 | -- | 17.1 | 24.1 | 22.6 | 22.8

| Search Agent

| HLE w/ tool | 35.8 | 19.0 | -- | 47.5 | 48.5 | 47.4

| Browsecomp | 48.1 | 41.1 | -- | 63.8 | 61.0 | 61.0

| Browsecomp-zh | 49.5 | 42.9 | -- | 69.9 | 62.1 | 69.5

| WideSearch | 47.2 | 40.4 | -- | 60.5 | 61.1 | 57.1

| Seal-0 | 34.2 | 45.1 | -- | 44.1 | 47.2 | 41.4

| Multilingualism

| MMMLU | 86.2 | 78.2 | 83.4 | 86.7 | 85.9 | 85.2

| MMLU-ProX | 78.5 | 74.5 | 77.9 | 82.2 | 82.2 | 81.0

| NOVA-63 | 51.9 | 51.1 | 55.4 | 58.6 | 58.1 | 57.1

| INCLUDE | 81.8 | 74.0 | 81.0 | 82.8 | 81.6 | 79.7

| Global PIQA | 88.5 | 84.1 | 85.7 | 88.4 | 87.5 | 86.6

| PolyMATH | 67.3 | 54.0 | 60.1 | 68.9 | 71.2 | 64.4

| WMT24++ | 80.7 | 74.4 | 75.8 | 78.3 | 77.6 | 76.3

| MAXIFE | 85.3 | 83.7 | 83.2 | 87.9 | 88.0 | 86.6

CodeForces: evaluated on our own query set.
TAU2-Bench: we follow the official setup except for the airline domain, where all models are evaluated by applying the fixes proposed in the Claude Opus 4.5 system card.
Search Agent: most search agents built on our model adopt a simple context-folding strategy(256k): once the cumulative Tool Response length reaches a preset threshold, earlier Tool Responses are pruned from the history to keep the context within limits.
WideSearch: we use a 256k context window without any context management.
MMLU-ProX: we report the averaged accuracy on 29 languages.
WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL.
MAXIFE: we report the accuracy on English + multilingual original prompts (totally 23 settings).
Empty cells (--) indicate scores not yet available or not applicable.

Vision Language#

| STEM and Puzzle

| MMMU | 79.0 | 79.6 | 80.6 | 83.9 | 82.3 | 81.4

| MMMU-Pro | 67.3 | 68.4 | 69.3 | 76.9 | 75.0 | 75.1

| MathVision | 71.9 | 71.1 | 74.6 | 86.2 | 86.0 | 83.9

| Mathvista(mini) | 79.1 | 79.8 | 85.8 | 87.4 | 87.8 | 86.2

| DynaMath | 81.4 | 78.8 | 82.8 | 85.9 | 87.7 | 85.0

| ZEROBench | 3 | 4 | 4 | 9 | 10 | 8

| ZEROBench_sub | 27.3 | 26.3 | 28.4 | 36.2 | 36.2 | 34.1

| VlmsAreBlind | 75.8 | 85.5 | 79.5 | 96.7 | 96.9 | 97.0

| BabyVision | 20.9 | 18.6 | 22.2 | 40.2 / 34.5 | 44.6 / 34.8 | 38.4 / 29.6

| General VQA

| RealWorldQA | 79.0 | 70.3 | 81.3 | 85.1 | 83.7 | 84.1

| MMStar | 74.1 | 73.8 | 78.7 | 82.9 | 81.0 | 81.9

| MMBenchEN-DEV-v1.1 | 86.8 | 88.3 | 89.7 | 92.8 | 92.6 | 91.5

| SimpleVQA | 56.8 | 57.6 | 61.3 | 61.7 | 56.0 | 58.3

| HallusionBench | 63.2 | 59.9 | 66.7 | 67.6 | 70.0 | 67.9

| Text Recognition and Document Understanding

| OmniDocBench1.5 | 77.0 | 85.8 | 84.5 | 89.8 | 88.9 | 89.3

| CharXiv(RQ) | 68.6 | 67.2 | 66.1 | 77.2 | 79.5 | 77.5

| MMLongBench-Doc | 50.3 | -- | 56.2 | 59.0 | 60.2 | 59.5

| CC-OCR | 70.8 | 68.1 | 81.5 | 81.8 | 81.0 | 80.7

| AI2D_TEST | 88.2 | 87.0 | 89.2 | 93.3 | 92.9 | 92.6

| OCRBench | 82.1 | 76.6 | 87.5 | 92.1 | 89.4 | 91.0

| Spatial Intelligence

| ERQA | 54.0 | 45.0 | 52.5 | 62.0 | 60.5 | 64.8

| CountBench | 91.0 | 90.0 | 93.7 | 97.0 | 97.8 | 97.8

| RefCOCO(avg) | -- | -- | 91.1 | 91.3 | 90.9 | 89.2

| ODInW13 | -- | -- | 43.2 | 44.5 | 41.1 | 42.6

| EmbSpatialBench | 80.7 | 71.8 | 84.3 | 83.9 | 84.5 | 83.1

| RefSpatialBench | 9.0 | 2.2 | 69.9 | 69.3 | 67.7 | 63.5

| LingoQA | 62.4 | 12.8 | 66.8 | 80.8 | 82.0 | 79.2

| Hypersim | -- | -- | 11.0 | 12.7 | 13.0 | 13.1

| SUNRGBD | -- | -- | 34.9 | 36.2 | 35.4 | 33.4

| Nuscene | -- | -- | 13.9 | 15.4 | 15.2 | 14.6

| Video Understanding

| VideoMME(w sub.) | 83.5 | 81.1 | 83.8 | 87.3 | 87.0 | 86.6

| VideoMME(w/o sub.) | 78.9 | 75.3 | 79.0 | 83.9 | 82.8

The publisher's README is longer; it is cut here. Read the rest at the source.

Files

26 files · 30.3 GBWeights 30.2 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 26 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE	11.3 KB	50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
README.md	92.8 KB	0f9e794f6a0f6d3fcc9b050a522d52d7498080b082a6100814d6e8605c904b95
chat_template.jinja	7.76 KB	a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715
config.json	4.67 KB	3d8342d9eaa840fcfcb754184ba10ed9f48de47799f683d2ed424b93c20884ae
configuration.json	51 B	2d4464e2ead06bc9bc718c781309ad1e7baded626d66e8dcdc8b469ba185faf0
count_param_ratio.py	4.54 KB	d32cb6d653ab0a1f869200c96f5ab16d53dcb54bce2471385a8cc55c7e1c1e04
generation_config.json	244 B	303aba891d66ab63908a7b3cc9163bcb835fdf8b9f6301c73216f3f1eb3992dd
merges.txt	3.35 MB	a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model.safetensors-00001-of-00011.safetensors	5.13 GB	0b01785e669196ff2fe4f9cd4d19439872bb06fb18effc287725d4096abeebbe
model.safetensors-00002-of-00011.safetensors	1.79 GB	8b4cf248fc6f0f2eee0da1a868d8f7b45c65b4681d3d5446cc591a8017ba6ec5
model.safetensors-00003-of-00011.safetensors	1.39 GB	d85936c75ca775cd3ffc4dc58c973b43e9b5dc24caab5abfac960164023e2a13
model.safetensors-00004-of-00011.safetensors	1.39 GB	20c35f321c4e8b834c4a4e1e312e55eeb4298ce5e960070bf2b42b73e17d57ed
model.safetensors-00005-of-00011.safetensors	1.39 GB	cb74599dd6cece8bd37bfe075dfa97615ef9276c65c957bc53252f2280386ffa
model.safetensors-00006-of-00011.safetensors	1.39 GB	92df5e75752ae53ab86fdc381a36c3c40a7ae99a0f113a5a217c1f57e272c6c9
model.safetensors-00007-of-00011.safetensors	1.39 GB	b519c144601884c2c051efa4e926529c8f2210bdb4b34c7597ab79d2b10d14a9
model.safetensors-00008-of-00011.safetensors	3.52 GB	104ee5a904437fec15e93a35f6ec32f165ad6d557df99c571497357cb82dfc2f
model.safetensors-00009-of-00011.safetensors	5.35 GB	71a153d882242734a1fc7e000734727f00f6ec8ca70b044f5e44fcf97736ef8f
model.safetensors-00010-of-00011.safetensors	5.35 GB	146745698b9f21940e2982beb1816a0eef3b80d77ab9cd884695b9a08c2697eb
model.safetensors-00011-of-00011.safetensors	2.15 GB	d947ce7483c4109b55039f1359f4494d22390cf123568100abd89816802f097d
model.safetensors.index.json	195 KB	8d2252b5507242ac58adf024541090843e8866527e3919f5fd5f2bc8241a770b
preprocessor_config.json	390 B	27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
tokenizer.json	12.8 MB	5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
tokenizer_config.json	16.7 KB	316230d6a809701f4db5ea8f8fc862bc3a6f3229c937c174e674ff3ca0a64ac8
video_preprocessor_config.json	385 B	7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json	6.72 MB	ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003

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

Upstream commit	Date	Contents
8f0c09f227 pinned now	2026-11-15 02:35 UTC	26 files · 30.3 GB

Use it

$ fw get Qwen/Qwen3.5-27B-GPTQ-Int4
# manifest sha256 b557bece712a… · 30.3 GB · 26 files
$ fw verify ./Qwen3.5-27B-GPTQ-Int4 Qwen/Qwen3.5-27B-GPTQ-Int4

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

$ python3 fw.py get https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-27B-GPTQ-Int4.json --dir ./Qwen3.5-27B-GPTQ-Int4
$ python3 fw.py verify ./Qwen3.5-27B-GPTQ-Int4 ./Qwen__Qwen3.5-27B-GPTQ-Int4.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3.5-27B-GPTQ-Int4 --revision 8f0c09f227ae570e79617c6d9172b59df9c16081 --local-dir ./Qwen3.5-27B-GPTQ-Int4

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForImageTextToText, AutoProcessor
processor = AutoProcessor.from_pretrained("Qwen/Qwen3.5-27B-GPTQ-Int4", revision="8f0c09f227ae570e79617c6d9172b59df9c16081")
model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.5-27B-GPTQ-Int4", revision="8f0c09f227ae570e79617c6d9172b59df9c16081", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve Qwen/Qwen3.5-27B-GPTQ-Int4 --revision 8f0c09f227ae570e79617c6d9172b59df9c16081

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: 50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
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:

Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject: Qwen3.5-27B-GPTQ-Int4Date: 2026-11-15Commit: 8f0c09fSigned: 2DC28CC7B26A283B ✓

Upstream: Qwen/Qwen3.5-27B-GPTQ-Int4
Pinned commit: 8f0c09f227ae570e79617c6d9172b59df9c16081
Manifest: Qwen3.5-27B-GPTQ-Int4.json · .minisig
Manifest sha256: b557bece712abdf989a94917d6d64c62481adf145e3a862fd15ce0b5b8913a95
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 02:35 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-27B-GPTQ-Int4.json
$ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-27B-GPTQ-Int4.json.minisig
$ minisign -Vm Qwen3.5-27B-GPTQ-Int4.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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3.5-27B-GPTQ-Int4

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. Qwen3.5-27B-GPTQ-Int4.json. Provenance. Takedown history: none.

Source

huggingface.co/Qwen/Qwen3.5-27B-GPTQ-Int4

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

Qwen3.5-27B-GPTQ-Int4

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

Qwen3.5-27B-GPTQ-Int4#

Qwen3.5 Highlights#

Model Overview#

Benchmark Results#

Language#

Vision Language#

Files

Use it

License

Provenance

How to verify

Model tree

Related models