# Qwen3.8-27B by Qwen: Open-Weight Model
Source: https://savrn.com/models/qwen3-8-27b
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve Qwen3.8-27B (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 24, 2026.

[Qwen3.8-27B on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen3-8-27b/gpus)

## SAVRN's Notes on Qwen3.8-27B

27.8B parameters reading image and text over a 262,144-token context: 66.7 GB at 16-bit fits one 192 GB MI300X at $1.85 an hour, 33.3 GB at 8-bit, 16.7 GB at 4-bit — a single card covers every precision, which is the whole story for a model this capable at this footprint. The 55.6 GB of weights ship as 18 safetensors files. First published 2026-08-05.

The variant forest is dense: FP8, NVFP4, GGUF, AWQ-INT4 and MLX builds at 4, 5, 6 and 8 bit all derive from it on the page. Hosted, the Index lists Cerebras at $0.99 in and $1.49 out per million tokens, DeepInfra $0.20 and $2.50, Novita $0.42 and $3.00, OVHcloud $0.47 and $3.19 — run the tokens-per-hour ledger before renting. Reported GPQA Diamond is 89.2, and the card promises a hosted version with 1M context coming.

SAVRN Research

## Model Card

By Qwen, published under apache-2.0, revision 1d4bf0f2ff60.

[!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, TokenSpeed, etc.

[!Tip] For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by [Qwen Cloud](https://www.qwencloud.com). In particular, Qwen3.8-27B will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the [Qwen3.8-27B Overview](https://www.qwencloud.com/models/qwen3.8-27b). The service is coming soon. Stay tuned for updates.

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.

[Read the full model card (2,690 words)](https://savrn.com/models/qwen3-8-27b/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/Qwen3.8-27B

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

1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0

First published

2026-08-05

Last updated

2026-08-14

## Files and Weights

32 files, 55.6 GB in total. The weights are 18 files totalling 55.6 GB in safetensors.

Weights18 files · 55.6 GB

Configuration5 files · 117.5 KB

Tokenizer4 files · 22.9 MB

Documentation2 files · 76.6 KB

Other2 files · 9.2 KB

Repository1 file · 1.6 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model-00001-of-00018.safetensors | Weights | 4.0 GB | ba0ce20aae48 |
| model-00002-of-00018.safetensors | Weights | 3.0 GB | 06a148c01bfb |
| model-00003-of-00018.safetensors | Weights | 2.5 GB | 2e1bf62cbcd4 |
| model-00004-of-00018.safetensors | Weights | 4.0 GB | 511e34063187 |
| model-00005-of-00018.safetensors | Weights | 2.1 GB | 635cb53446dc |
| model-00006-of-00018.safetensors | Weights | 4.0 GB | 0bc5214fac60 |
| model-00007-of-00018.safetensors | Weights | 2.1 GB | 80b0c49033e9 |
| model-00008-of-00018.safetensors | Weights | 4.0 GB | 7192c5b66185 |
| model-00009-of-00018.safetensors | Weights | 2.1 GB | af3c48cc37af |
| model-00010-of-00018.safetensors | Weights | 4.0 GB | 163490a76f3b |
| model-00011-of-00018.safetensors | Weights | 2.1 GB | 5f3ae1b948ae |
| model-00012-of-00018.safetensors | Weights | 4.0 GB | a3de1c711467 |
| model-00013-of-00018.safetensors | Weights | 2.1 GB | 06ab79a41f74 |
| model-00014-of-00018.safetensors | Weights | 4.0 GB | 4138ed946030 |
| model-00015-of-00018.safetensors | Weights | 2.1 GB | 69224e27b9de |
| model-00016-of-00018.safetensors | Weights | 4.0 GB | 73cb9a1089fb |
| model-00017-of-00018.safetensors | Weights | 2.1 GB | beb51f010561 |
| model-00018-of-00018.safetensors | Weights | 3.4 GB | 1d3479509e21 |
| config.json | Configuration | 4.3 KB | — |
| generation_config.json | Configuration | 202 B | — |
| model.safetensors.index.json | Configuration | 112.2 KB | — |
| preprocessor_config.json | Configuration | 390 B | — |
| video_preprocessor_config.json | Configuration | 385 B | — |
| LICENSE | Documentation | 11.5 KB | — |
| README.md | Documentation | 65.0 KB | — |
| chat_template.jinja | Other | 9.0 KB | — |
| crc32.txt | Other | 238 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 3.4 MB | — |
| tokenizer.json | Tokenizer | 12.8 MB | 0997f410c57a |
| tokenizer_config.json | Tokenizer | 17.9 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/Qwen3.8-27B)

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 diamondComparison conditions not established | 89.2 | [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B) Reported by a third party | Evaluated revision not stated | 2026-08-14 |
| ScaleAI/SWE-bench_Pro | Task SWE_Bench_ProMetric SWE_Bench_ProSetup Evaluated with the Claude Code harness, temp=1.0, top_p=0.95, 256K context; baseline models re-evaluated on the same refined task set.Comparison conditions not established | 61.7 | [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B) Reported by a third party | Evaluated revision not stated | 2026-08-14 |
| agents-last-exam/agents-last-exam | Task ale-cli-pass-rateMetric ale-cli-pass-rateSetup harness=claude_code; harness_variant=reasoning-max; attempted=104/105; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not…Comparison conditions not established | 19.0476 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task ale-cli-scoreMetric ale-cli-scoreSetup harness=claude_code; harness_variant=reasoning-max; attempted=104/105; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not…Comparison conditions not established | 43.5407 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task full-spectrum-pass-rateMetric full-spectrum-pass-rateSetup harness=claude_code; harness_variant=reasoning-max; attempted=55/55; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not an…Comparison conditions not established | 21.8182 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task full-spectrum-scoreMetric full-spectrum-scoreSetup harness=claude_code; harness_variant=reasoning-max; attempted=55/55; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not an…Comparison conditions not established | 42.5452 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task last-exam-pass-rateMetric last-exam-pass-rateSetup harness=claude_code; harness_variant=reasoning-max; attempted=35/38; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not an…Comparison conditions not established | 2.63158 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task last-exam-scoreMetric last-exam-scoreSetup harness=claude_code; harness_variant=reasoning-max; attempted=35/38; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not an…Comparison conditions not established | 14.7264 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task near-term-pass-rateMetric near-term-pass-rateSetup harness=claude_code; harness_variant=reasoning-max; attempted=66/67; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not an…Comparison conditions not established | 31.3433 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task near-term-scoreMetric near-term-scoreSetup harness=claude_code; harness_variant=reasoning-max; attempted=66/67; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not an…Comparison conditions not established | 60.0256 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task overall-pass-rateMetric overall-pass-rateSetup harness=claude_code; harness_variant=reasoning-max; attempted=148/152; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not…Comparison conditions not established | 20.3947 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| agents-last-exam/agents-last-exam | Task overall-scoreMetric overall-scoreSetup harness=claude_code; harness_variant=reasoning-max; attempted=148/152; official leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold score>=0.999. This is an official leaderboard export, not…Comparison conditions not established | 42.8848 | ALE official leaderboard Reported by a third party | Evaluated revision not stated | 2026-10-01 |
| cais/hle | Task hleMetric hleSetup Judged by GPT-4o.Comparison conditions not established | 30.8 | [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B) Reported by a third party | Evaluated revision not stated | 2026-08-14 |
| claw-eval/Claw-Eval | Task multimodalMetric multimodalSetup Reported as ClawEval-MM. Pass@3, the benchmark's own Pass³ methodology; card also reports a secondary 56.9 'Average' metric, not included here.Comparison conditions not established | 57.4 | [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B) Reported by a third party | Evaluated revision not stated | 2026-08-14 |
| datacurve/deep-swe | Task deep_sweMetric deep_sweComparison conditions not established | 42.2 | [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B) Reported by a third party | Evaluated revision not stated | 2026-08-14 |
| facebook/mmi | Task error-rateMetric error-rateComparison conditions not established | 41.1 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task mmi-valueMetric mmi-valueComparison conditions not established | 11.46 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task modality-presence-scoreMetric modality-presence-scoreComparison conditions not established | 18.09 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task pass-rate-lenientMetric pass-rate-lenientComparison conditions not established | 13.33 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task pass-rate-strictMetric pass-rate-strictComparison conditions not established | 9.18 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task precisionMetric precisionComparison conditions not established | 99.01 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task recallMetric recallComparison conditions not established | 16.93 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| harborframework/terminal-bench-2.1 | Task terminalbench_2_1Metric terminalbench_2_1Setup Row labeled "(Terminus)" as the harness; no further hyperparameter footnote given for this row.Comparison conditions not established | 73 | [Model Card](https://huggingface.co/Qwen/Qwen3.8-27B) Reported by a third party | Evaluated revision not stated | 2026-08-14 |
| internlm/WildClawBench | Task avg_timeMetric avg_timeComparison conditions not established | 516 | WildClawBench Reported by a third party | Evaluated revision not stated | 2026-08-16 |
| internlm/WildClawBench | Task overallMetric overallComparison conditions not established | 48.0152 | WildClawBench Reported by a third party | Evaluated revision not stated | 2026-08-16 |
| llamaindex/ExtractBench | Task longMetric longSetup Pipeline name: qwen3_8_27b_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 38.45 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task meanMetric meanSetup Pipeline name: qwen3_8_27b_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 89.75 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task mediumMetric mediumSetup Pipeline name: qwen3_8_27b_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 87.54 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task shortMetric shortSetup Pipeline name: qwen3_8_27b_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 94.68 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-24 |
| llamaindex/ParseBench | Task chartMetric chartSetup Pipeline name: qwen3_8_27b_thinking_parse_with_layout; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 69.17 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-08-28 |
| llamaindex/ParseBench | Task layoutMetric layoutSetup Pipeline name: qwen3_8_27b_thinking_parse_with_layout; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 69.9 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-08-28 |
| llamaindex/ParseBench | Task meanMetric meanSetup Pipeline name: qwen3_8_27b_thinking_parse_with_layout; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 70.79 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-08-28 |
| llamaindex/ParseBench | Task tableMetric tableSetup Pipeline name: qwen3_8_27b_thinking_parse_with_layout; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 66.82 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-08-28 |
| llamaindex/ParseBench | Task text_contentMetric text_contentSetup Pipeline name: qwen3_8_27b_thinking_parse_with_layout; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 88.28 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-08-28 |
| llamaindex/ParseBench | Task text_formattingMetric text_formattingSetup Pipeline name: qwen3_8_27b_thinking_parse_with_layout; served checkpoint: Qwen/Qwen3.8-27B-FP8Comparison conditions not established | 59.77 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-08-28 |

## 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 |
| --- | --- | --- | --- |
| Cerebras | $0.99 / $1.49 | input / output, per million tokens | Oct 24, 2026 |
| DeepInfra | $0.20 / $2.50 | input / output, per million tokens | Oct 24, 2026 |
| Novita | $0.42 / $3.00 | input / output, per million tokens | Oct 24, 2026 |
| OVHcloud | $0.47 / $3.19 | input / output, per million tokens | Oct 24, 2026 |

From the [SAVRN Index](https://savrn.com/ai-index/pricing/open-models).

## Built on This Model

- Quantized from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf)
- Derived from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf)
- Quantized from[Qwen3.8-27B-FP8](https://savrn.com/models/qwen3-8-27b-fp8)
- Derived from[Qwen3.8-27B-FP8](https://savrn.com/models/qwen3-8-27b-fp8)
- Quantized from[Qwen3.8-27B-MLX-4bit](https://savrn.com/models/qwen3-8-27b-mlx-4bit)
- Derived from[Qwen3.8-27B-MLX-4bit](https://savrn.com/models/qwen3-8-27b-mlx-4bit)
- Quantized from[Qwen3.8-27B-MLX-8bit](https://savrn.com/models/qwen3-8-27b-mlx-8bit)
- Derived from[Qwen3.8-27B-MLX-8bit](https://savrn.com/models/qwen3-8-27b-mlx-8bit)
- Quantized from[Qwen3.8-27B-MLX-6bit](https://savrn.com/models/qwen3-8-27b-mlx-6bit)
- Derived from[Qwen3.8-27B-MLX-6bit](https://savrn.com/models/qwen3-8-27b-mlx-6bit)
- Quantized from[Qwen3.8-27B-MLX-5bit](https://savrn.com/models/qwen3-8-27b-mlx-5bit)
- Derived from[Qwen3.8-27B-MLX-5bit](https://savrn.com/models/qwen3-8-27b-mlx-5bit)
- Quantized from[Qwen3.8-27B-Uncensored-GGUF](https://savrn.com/models/qwen3-8-27b-uncensored-gguf)
- Derived from[Qwen3.8-27B-Uncensored-GGUF](https://savrn.com/models/qwen3-8-27b-uncensored-gguf)
- Quantized from[Huihui-Qwen3.8-27B-abliterated-GGUF](https://savrn.com/models/huihui-qwen3-8-27b-abliterated-gguf)
- Derived from[Huihui-Qwen3.8-27B-abliterated-GGUF](https://savrn.com/models/huihui-qwen3-8-27b-abliterated-gguf)
- Quantized from[Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF](https://savrn.com/models/qwen3-8-27b-imatrix-nvfp4-mtp-gguf)
- Derived from[Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF](https://savrn.com/models/qwen3-8-27b-imatrix-nvfp4-mtp-gguf)
- Quantized from[Ternary-Bonsai-2-27B-gguf](https://savrn.com/models/ternary-bonsai-2-27b-gguf-2)
- Derived from[Ternary-Bonsai-2-27B-gguf](https://savrn.com/models/ternary-bonsai-2-27b-gguf-2)
- Quantized from[Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF](https://savrn.com/models/qwen3-8-27b-uncensored-hauhaucs-aggressive-mtp-gguf)
- Derived from[Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF](https://savrn.com/models/qwen3-8-27b-uncensored-hauhaucs-aggressive-mtp-gguf)
- Quantized from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf-3)
- Derived from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf-3)
- Adapter of[JEV-27B-VL](https://savrn.com/models/jev-27b-vl)
- Derived from[JEV-27B-VL](https://savrn.com/models/jev-27b-vl)
- Quantized from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf-6)
- Derived from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf-6)
- Quantized from[Qwen3.8-27B-NVFP4](https://savrn.com/models/qwen3-8-27b-nvfp4)
- Derived from[Qwen3.8-27B-NVFP4](https://savrn.com/models/qwen3-8-27b-nvfp4)
- Quantized from[Dirk-Qwen3.8-27B-GGUF](https://savrn.com/models/dirk-qwen3-8-27b-gguf)
- Derived from[Dirk-Qwen3.8-27B-GGUF](https://savrn.com/models/dirk-qwen3-8-27b-gguf)
- Quantized from[Qwen3.8-27B-GSQ-RCO-GGUF](https://savrn.com/models/qwen3-8-27b-gsq-rco-gguf)
- Derived from[Qwen3.8-27B-GSQ-RCO-GGUF](https://savrn.com/models/qwen3-8-27b-gsq-rco-gguf)
- Quantized from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf-2)
- Derived from[Qwen3.8-27B-GGUF](https://savrn.com/models/qwen3-8-27b-gguf-2)
- Quantized from[Qwen3.8-27B-AWQ-INT4](https://savrn.com/models/qwen3-8-27b-awq-int4)
- Derived from[Qwen3.8-27B-AWQ-INT4](https://savrn.com/models/qwen3-8-27b-awq-int4)
- Quantized from[Qwen3.8-27B-OBLITERATED](https://savrn.com/models/qwen3-8-27b-obliterated)
- Derived from[Qwen3.8-27B-OBLITERATED](https://savrn.com/models/qwen3-8-27b-obliterated)

## Compare Qwen3.8-27B

- [gemma-4-26B-A4B-it vs Qwen3.8-27B](https://savrn.com/models/compare/gemma-4-26b-a4b-it-vs-qwen3-8-27b)
- [gemma-4-31B-it vs Qwen3.8-27B](https://savrn.com/models/compare/gemma-4-31b-it-vs-qwen3-8-27b)
- [Qwen3.6-27B vs Qwen3.8-27B](https://savrn.com/models/compare/qwen3-6-27b-vs-qwen3-8-27b)

## Questions About Qwen3.8-27B

### How much GPU memory does Qwen3.8-27B 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 Qwen3.8-27B 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 Qwen3.8-27B commercially?

Yes. Qwen3.8-27B 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 Qwen3.8-27B'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-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

### [Qwen3.5-27B](https://savrn.com/models/qwen3-5-27b)

[Qwen](https://savrn.com/model-publishers/qwen)

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. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. Empty cells (--) indicate scores not…

Open weights apache-2.0 27.8B parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-5-27b)

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

- [1d4bf0f2ff60](https://savrn.com/models/qwen3-8-27b/versions/1d4bf0f2ff60) · current 2026-10-24

## 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/Qwen3.8-27B)
- [How the hub is built](https://savrn.com/model-hub/methodology)