SAVRN
Search Contact SAVRN

Open-weight model

Qwen3.8-27B-GGUF

by Jake jakeatx/Qwen3.8-27B-GGUF

Unified release repository for Qwen3.8-27B quantizations, fine-tunes, and speculative decoding configurations optimized for llamAmpere on SM86 (RTX 3090 / 3090 Ti). Run with native MTP speculative drafting

Parameters
Context
Weights53.2 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads

Model Card

By Jake, published under apache-2.0, revision 25080521acad.

Unified release repository for Qwen3.8-27B quantizations, fine-tunes, and speculative decoding configurations optimized for llamAmpere on SM86 (RTX 3090 / 3090 Ti). Run with native MTP speculative drafting

Read Jake's full model card

Qwen3.8-27B GGUF Model Hub

Unified release repository for Qwen3.8-27B quantizations, fine-tunes, and speculative decoding configurations optimized for llamAmpere on SM86 (RTX 3090 / 3090 Ti).

Available Models

File Base Architecture BPW / Quant MTP Drafter Target Hardware / Fit
qwen3.8-27b-ternary-mtp.gguf Prism ML Ternary Bonsai 2 27B 1.75 bpw (PTQ1_0) Native 1-layer MTP 5.81 GiB; fits 262K context under 24 GB VRAM
Qwen3.8-27B-ATX-4-XS.gguf Qwen3.8-27B Base 4.56 bpw (ATX-IQ4_XS-M) Native 1-layer MTP 14.52 GiB; 245K context populated under 22.6 GB ready
ATX-Swift-Qwen3.8-27B-Uncensored-IQ4_XS-M.gguf Qwen3.8-27B Swift Uncensored 4.56 bpw (IQ4_XS-M) Native 1-layer MTP 15.58 GiB
Qwopus3.8-27B-Flash-ATX-IQ4_XS-M.gguf Qwopus3.8-27B Flash 4.56 bpw (IQ4_XS-M) Native 1-layer MTP 15.58 GiB

Running with llamAmpere

Build the SM86 runtime:

cmake -S . -B build-sm86 -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON -DGGML_CUDA_FA=ON \
      -DCMAKE_CUDA_ARCHITECTURES=86 -DGGML_NATIVE=ON
cmake --build build-sm86 -j8 --target llama-server

Run with native MTP speculative drafting:

./build-sm86/bin/llama-server \
  -m qwen3.8-27b-ternary-mtp.gguf \
  -c 32768 -b 4096 -ub 1024 -t 8 -ngl 99 -fa on -ctk q8_0 -ctv turbo3 \
  --spec-type draft-mtp --spec-draft-n-max 3 --spec-draft-p-min 0

Identity and Version

Repository
jakeatx/Qwen3.8-27B-GGUF
Publisher
Jake
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
mtp
Revision
25080521acadda1497cbb79b1e6e3c26a750bb1b
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

8 files, 53.2 GB in total. The weights are 6 files totalling 53.2 GB in gguf.

Weights6 files · 53.2 GB
Documentation1 file · 1.5 KB
Repository1 file · 1.9 KB
Every file
FileTypeSizeSHA-256
ATX-Swift-Qwen3.8-27B-Uncensored-IQ4_XS-M.ggufWeights15.6 GB 51880ce0f15a
Qwen3.8-27B-ATX-4-XS.ggufWeights15.6 GB 5cf05ad901dc
Qwopus3.8-27B-Flash-ATX-IQ4_XS-M.ggufWeights15.7 GB 733198976d76
imatrix_qwopus_flash.ggufWeights13.6 MB 3ad1f03fe39a
imatrix_swift_unc.ggufWeights13.6 MB ef52688ab733
qwen3.8-27b-ternary-mtp.ggufWeights6.2 GB f24d2d2ce73f
README.mdDocumentation1.5 KB
.gitattributesRepository1.9 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
53.2 GB
Download from Jake

Released by Jake through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published53.2 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Qwen3.8-27B-GGUF

Can I use Qwen3.8-27B-GGUF commercially?

Yes. Qwen3.8-27B-GGUF 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.