Open-weight model
Qwen3.8-27B-ULT3-QNext-Stage1.1
by David Belton DavidAU/Qwen3.8-27B-ULT3-QNext-Stage1.1
Qwen3.8-27B-ULT3-QNext-Stage1.1 is a model from David Belton, released under Apache License 2.0 (access requested at publisher). It has 27.8B parameters. At 16-bit it needs about 66.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 2 downloads a month.
This model is part of this project: https://huggingface.co/DavidAU/Qwen3.8-27B-UltimateDetails2-stage1The-Harley-Pelican This is a work in progress, if you want to be notified the FINAL release, go to ABOVE REPO to request access. - Stage 1 built, tested.
Runs On
What it takes to serve Qwen3.8-27B-ULT3-QNext-Stage1.1 (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 (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 27.8 GB | 33.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 13.9 GB | 16.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x 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, read Oct 7, 2026.
Qwen3.8-27B-ULT3-QNext-Stage1.1 on every accelerator the SAVRN Index prices, at every precision
Model Card
By David Belton, published under apache-2.0, revision 536e76a30c7d.
This model is part of this project:
https://huggingface.co/DavidAU/Qwen3.8-27B-UltimateDetails2-stage1__The-Harley-Pelican
This is a work in progress, if you want to be notified the FINAL release, go to ABOVE REPO to request access.
- Stage 1 built, tested.
- Stage 1.1 and Stage 1.5 => Built, in testing.
Benches: [see full project notes/benches at above repo]
arc/c arc/e boolq hswag obkqa piqa wino
[NEW BRANCH CORE START]
Ultimate 3 [Qwen Next Branch; ground up build, components first, then combine.]
Qwen3.8-27B-ULT3-QNext-Stage1 => Qnext Reasoning Only Training Mild.
mxfp8 0.617,0.809,0.906,...
Stage 1.1 :
Qwen3.8-27B-ULT3-QNext-Stage1.1
mxfp8 0.622,0.801,0.901,...
Stage 1.5
- pending
[QWENS]
[base, non heretic, untuned]
Qwen3.8-27B-Instruct:
mxfp8 0.591,0.782,0.896,0.746,0.448,0.801,0.711
Qwen3.6-27B-Instruct:
mxfp8 0.647,0.803,0.910,0.773,0.450,0.806,0.742
Qwen3.5-27B-Instruct:
mxfp8 0.557,0.711,0.868,0.533,0.452,0.706,0.695
Identity and Version
- Repository
- DavidAU/Qwen3.8-27B-ULT3-QNext-Stage1.1
- Publisher
- David Belton
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 27.8B parameters
- Languages
- Not stated by the source
- Revision
- 536e76a30c7d5ae3ae06cf9ba1bbc6d9c8a8e9c3
- First published
- 2026-10-03
- Last updated
- 2026-10-05
Files and Weights
27 files, 55.6 GB in total. The weights are 18 files totalling 55.6 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00002-of-00018.safetensors | Weights | 3.0 GB | — |
| model-00003-of-00018.safetensors | Weights | 2.5 GB | — |
| model-00004-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00005-of-00018.safetensors | Weights | 2.1 GB | — |
| model-00006-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00007-of-00018.safetensors | Weights | 2.1 GB | — |
| model-00008-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00009-of-00018.safetensors | Weights | 2.1 GB | — |
| model-00010-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00011-of-00018.safetensors | Weights | 2.1 GB | — |
| model-00012-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00013-of-00018.safetensors | Weights | 2.1 GB | — |
| model-00014-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00015-of-00018.safetensors | Weights | 2.1 GB | — |
| model-00016-of-00018.safetensors | Weights | 4.0 GB | — |
| model-00017-of-00018.safetensors | Weights | 2.1 GB | — |
| model-00018-of-00018.safetensors | Weights | 3.4 GB | — |
| config.json | Configuration | 4.5 KB | — |
| generation_config.json | Configuration | 213 B | — |
| model.safetensors.index.json | Configuration | 112.2 KB | — |
| processor_config.json | Configuration | 1.2 KB | — |
| README.md | Documentation | 1.5 KB | — |
| chat_template.jinja | Other | 9.0 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | — |
| tokenizer_config.json | Tokenizer | 16.4 KB | — |
License and Download
- License
- apache-2.0
- Access
- Access requested at publisher
- Download size
- 55.6 GB
David Belton grants access through its official repository on Hugging Face. Read the license.
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.
Questions About Qwen3.8-27B-ULT3-QNext-Stage1.1
How much GPU memory does Qwen3.8-27B-ULT3-QNext-Stage1.1 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-ULT3-QNext-Stage1.1 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-ULT3-QNext-Stage1.1 commercially?
Yes. Qwen3.8-27B-ULT3-QNext-Stage1.1 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.