# Qwen3.5-27B by Qwen: Open-Weight Model Source: https://savrn.com/models/qwen3-5-27b Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Qwen3.5-27B (27.8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 55.6 GB | 66.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 27.8 GB | 33.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 13.9 GB | 16.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [Qwen3.5-27B on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen3-5-27b/gpus) ## SAVRN's Notes on Qwen3.5-27B 27.8B parameters in a dense multimodal body, released February 2026: it reads images and text over a 262,144-token context. Memory runs 66.7 GB at 16-bit, 33.3 GB at 8-bit and 16.7 GB at 4-bit — the cheapest listed setup is one 192 GB MI300X at $1.85 an hour, and at 4-bit a single workstation card holds it. The repo is 11 safetensors shards totalling 55.6 GB, and downloads run 1.9M a month. Apache 2.0 permits commercial use with notices kept. The card states compatibility with Transformers, vLLM, SGLang and KTransformers. Reported results on the page include SWE-bench 72.4, MMLU-Pro 86.1, Terminal-Bench 2.0 41.6 and ScreenSpot-Pro 70.3, plus HLE at 48.5 with tools against 24.3 chain-of-thought — a gap that says tool access is not optional for this model's harder tasks. None of these is a SAVRN measurement. If you would rather rent by the token, the Index observes DeepInfra at $0.26 in and $2.60 out per million tokens and Novita at $0.30 and $2.40, both read Oct 1, 2026. Against $1.85 an hour for self-hosting, hosted inference wins at low volume and loses quickly at sustained load — run the arithmetic at your actual traffic before committing to a card. SAVRN Research ## Model Card By Qwen, published under apache-2.0, revision fc05daec18b0. [!Note] This repository contains 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: [Read the full model card (3,407 words)](https://savrn.com/models/qwen3-5-27b/card) ## Configuration Architecture Qwen3_5ForConditionalGeneration Context length (tokens) 262,144 Layers 64 Hidden size 5,120 Feed-forward size 17,408 Attention heads 24 Key/value heads 4 Head dimension 256 Vocabulary size 248,320 Model type qwen3_5 ## Identity and Version Repository Qwen/Qwen3.5-27B Publisher Qwen Task Image and text to text Modality Image and text Library transformers Parameters 27.8B parameters Languages Not stated by the source Revision fc05daec18b0a78c049392ed2e771dde82bdf654 First published 2026-02-24 Last updated 2026-04-24 ## Files and Weights 24 files, 55.6 GB in total. The weights are 11 files totalling 55.6 GB in safetensors. Weights11 files · 55.6 GB Configuration5 files · 131.8 KB Tokenizer4 files · 22.9 MB Documentation2 files · 103.8 KB Other1 file · 7.8 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors-00001-of-00011.safetensors | Weights | 5.3 GB | 9019228d172c | | model.safetensors-00002-of-00011.safetensors | Weights | 5.3 GB | 890ef00c920b | | model.safetensors-00003-of-00011.safetensors | Weights | 5.3 GB | 8aca03689ad0 | | model.safetensors-00004-of-00011.safetensors | Weights | 5.3 GB | 20f539430c60 | | model.safetensors-00005-of-00011.safetensors | Weights | 5.3 GB | 57a0c074c654 | | model.safetensors-00006-of-00011.safetensors | Weights | 5.3 GB | cfa4e6fbfc60 | | model.safetensors-00007-of-00011.safetensors | Weights | 5.3 GB | d426963325b2 | | model.safetensors-00008-of-00011.safetensors | Weights | 5.4 GB | fe60dbb9d253 | | model.safetensors-00009-of-00011.safetensors | Weights | 5.3 GB | 71a153d88224 | | model.safetensors-00010-of-00011.safetensors | Weights | 5.3 GB | 146745698b9f | | model.safetensors-00011-of-00011.safetensors | Weights | 2.1 GB | d947ce7483c4 | | config.json | Configuration | 4.1 KB | — | | generation_config.json | Configuration | 244 B | — | | model.safetensors.index.json | Configuration | 126.6 KB | — | | preprocessor_config.json | Configuration | 390 B | — | | video_preprocessor_config.json | Configuration | 385 B | — | | LICENSE | Documentation | 11.3 KB | — | | README.md | Documentation | 92.4 KB | — | | chat_template.jinja | Other | 7.8 KB | — | | .gitattributes | Repository | 1.6 KB | — | | merges.txt | Tokenizer | 3.4 MB | — | | tokenizer.json | Tokenizer | 12.8 MB | 5f9e4d4901a9 | | tokenizer_config.json | Tokenizer | 16.7 KB | — | | vocab.json | Tokenizer | 6.7 MB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 55.6 GB [Download from Qwen](https://modelscope.cn/models/Qwen/Qwen3.5-27B) Released by Qwen through ModelScope. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Evaluations Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical. | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | Idavidrein/gpqa | Task diamondMetric diamondSetup GPQA DiamondComparison conditions not established | 81.8182 | [EvalEval](https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5b/a4/5ba4cf19-18b3-4d08-bad0-ef29422cb18a.json) Reported by a third party | Evaluated revision not stated | 2026-04-20 | | Idavidrein/gpqa | Task diamondMetric diamondComparison conditions not established | 85.5 | [Model Card](https://huggingface.co/Qwen/Qwen3.5-27B) Reported by a third party | Evaluated revision not stated | 2026-02-25 | | MMMU/MMMU_Pro | Task mmmu_pro_visionMetric mmmu_pro_visionComparison conditions not established | 75 | [Model Card](https://huggingface.co/Qwen/Qwen3.5-27B) Reported by a third party | Evaluated revision not stated | 2026-04-28 | | MathArena/aime_2026 | Task MathArena/aime_2026Metric MathArena/aime_2026Comparison conditions not established | 90.83 | Official MathArena Evaluation Reported by a third party | Evaluated revision not stated | 2026-03-17 | | MathArena/hmmt_feb_2026 | Task MathArena/hmmt_feb_2026Metric MathArena/hmmt_feb_2026Comparison conditions not established | 81.06 | Official MathArena Evaluation Reported by a third party | Evaluated revision not stated | 2026-03-17 | | SWE-bench/SWE-bench_Verified | Task swe_bench_%_resolvedMetric swe_bench_%_resolvedComparison conditions not established | 72.4 | [Model Card](https://huggingface.co/Qwen/Qwen3.5-27B) Reported by a third party | Evaluated revision not stated | 2026-02-03 | | TIGER-Lab/MMLU-Pro | Task mmlu_proMetric mmlu_proComparison conditions not established | 86.1 | [EvalEval](https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/15/df/15df0778-3ca6-4ff9-9b34-41f74dc4ced4.json) Reported by a third party | Evaluated revision not stated | 2026-06-30 | | cais/hle | Task hleMetric hleSetup with toolsComparison conditions not established | 48.5 | [Model Card](https://huggingface.co/Qwen/Qwen3.5-27B) Reported by a third party | Evaluated revision not stated | 2026-02-25 | | cais/hle | Task hleMetric hleSetup chain of thoughtComparison conditions not established | 24.3 | [Model Card](https://huggingface.co/Qwen/Qwen3.5-27B) Reported by a third party | Evaluated revision not stated | 2026-02-25 | | harborframework/terminal-bench-2.0 | Task terminalbench_2Metric terminalbench_2Comparison conditions not established | 41.6 | [Model Card](https://huggingface.co/Qwen/Qwen3.5-27B) Reported by a third party | Evaluated revision not stated | 2026-02-25 | | likaixin/ScreenSpot-Pro | Task overallMetric overallComparison conditions not established | 70.3 | [Model Card](https://huggingface.co/Qwen/Qwen3.5-27B) Reported by a third party | Evaluated revision not stated | 2026-03-18 | ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 55.6 GB | | 16-bit | 55.6 GB | | 8-bit | 27.8 GB | | 4-bit | 13.9 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Hosted Prices | Host | Input / output | Unit | Observed | | --- | --- | --- | --- | | DeepInfra | $0.26 / $2.60 | input / output, per million tokens | Oct 25, 2026 | | Novita | $0.30 / $2.40 | input / output, per million tokens | Oct 25, 2026 | From the [SAVRN Index](https://savrn.com/ai-index/pricing/open-models). ## Built on This Model - Derived from[Qwen3.5-KETI-HAECHI-27B](https://savrn.com/models/qwen3-5-keti-haechi-27b) - Derived from[GameScaling-27B-S3](https://savrn.com/models/gamescaling-27b-s3) - Derived from[GameScaling-27B-S1](https://savrn.com/models/gamescaling-27b-s1) - Derived from[TerminalHorizon-27B](https://savrn.com/models/terminalhorizon-27b) - Derived from[chatter-27b-v1.1](https://savrn.com/models/chatter-27b-v1-1) ## Compare Qwen3.5-27B - [Qwen3.5-27B vs Qwen3.6-27B](https://savrn.com/models/compare/qwen3-5-27b-vs-qwen3-6-27b) - [Qwen3.5-27B vs Qwen3.6-35B-A3B](https://savrn.com/models/compare/qwen3-5-27b-vs-qwen3-6-35b-a3b) ## Questions About Qwen3.5-27B ### How much GPU memory does Qwen3.5-27B need? About 66.7 GB at 16-bit and 16.7 GB at 4-bit: the weights (27.8B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Qwen3.5-27B on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use Qwen3.5-27B commercially? Yes. Qwen3.5-27B is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is Qwen3.5-27B's context length? 262,144 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Image and text to text ### [Qwen3.8-27B](https://savrn.com/models/qwen3-8-27b) [Qwen](https://savrn.com/model-publishers/qwen) Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be… Open weights apache-2.0 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-8-27b) Model · Image and text to text ### [Qwen3.8-27B-FP8](https://savrn.com/models/qwen3-8-27b-fp8) [Qwen](https://savrn.com/model-publishers/qwen) Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be… Open weights apache-2.0 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-8-27b-fp8) Model · Image and text to text ### [Qwen3.6-27B](https://savrn.com/models/qwen3-6-27b) [Qwen](https://savrn.com/model-publishers/qwen) Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release delivers substantial upgrades, particularly in For more details, please refer to our blog post Qwen3.6-27B. Empty cells (--) indicate scores not yet available or not applicable. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API. Qwen3.6 can be served via APIs with popular inference frameworks. In… Open weights apache-2.0 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-6-27b) Model · Image and text to text ### [JEV-27B-VL](https://savrn.com/models/jev-27b-vl) [AutoTrust AI Lab](https://savrn.com/model-publishers/autotrust) The benchmark. ERQA (Embodied Reasoning Question Answering) is the benchmark Google DeepMind released with Gemini Robotics (March 2025) to measure whether a vision-language model understands the physical world a robot acts in. It has 400 multiple-choice questions about real robot and everyday scenes, with 1–16 images per question (287 questions have one image). 382 questions have 4 options and the rest 2–3, so chance is about 26%. ERQA is one of the standard embodied-reasoning benchmarks; Gemini Robotics-ER, PhysBrain and Hy-Embodied report it. With 400 questions the 95% interval of a score is about ±5 points. How we test. Each question is one choice decision through POST /v1/decide: the… Open weights apache-2.0 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/jev-27b-vl) Model · Image and text to text ### [Qwen3.8-27B-AWQ-INT4](https://savrn.com/models/qwen3-8-27b-awq-int4) [Cyankiwi](https://savrn.com/model-publishers/cyankiwi) Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be… Open weights apache-2.0 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-8-27b-awq-int4) Model · Image and text to text ### [Qwen3.8-27B-Uncensored](https://savrn.com/models/qwen3-8-27b-uncensored) [OrcaRouter](https://savrn.com/model-publishers/orcarouter) This model has had its safety alignment substantially removed via abliteration (orthogonalizing the refusal direction out of the residual stream). As a direct consequence: - It will comply with harmful, unethical, offensive, or illegal requests that the original Qwen3.8-27B would refuse. It has no meaningful built-in guardrails. - It is released strictly for legitimate research — interpretability, AI-safety and refusal-mechanism study, red-teaming, robustness evaluation, and controlled experiments. - You assume full responsibility and liability for how you use it and for everything it generates. Do not deploy it to end users or in production without adding your own safety, moderation, and… Access requested at publisher apache-2.0 27.8B parameters transformers [View model](https://savrn.com/models/qwen3-8-27b-uncensored) ## Qwen [All models and datasets](https://savrn.com/model-publishers/qwen) ## Versions - [fc05daec18b0](https://savrn.com/models/qwen3-5-27b/versions/fc05daec18b0) · current 2026-10-25 ## Explore More - [All image and text to text models](https://savrn.com/models/tasks/image-and-text-to-text) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Qwen website](https://qwen.ai/) - [Hugging Face record](https://huggingface.co/Qwen/Qwen3.5-27B) - [How the hub is built](https://savrn.com/model-hub/methodology)