Get the latest setups
Models/Qwen3.8/Qwen3.8 27B GGUF
Text / byteshape

Qwen3.8 27B GGUF

Qwen3.8-27B GGUF is a GGUF-quantized version of Qwen/Qwen3.8-27B, produced with ByteShape's ShapeLearn method. The published model card lists an Apache-2.0 license, image-text-to-text pipeline, the gguf tag, and base model Qwen/Qwen3.8-27B. ShapeLearn is described as learning per-tensor datatypes intended to maintain quality at low bitlengths, and this release is said to replace earlier ShapeLearn-Lite quantizations. The card states models went through a multi-benchmark evaluation suite covering math, coding, general knowledge, instruction following, and agentic tool use in thinking and instruct modes against a BF16 baseline. It also describes vision capability, a bundled MTP head, llama.cpp usage, speculative decoding options, a build requirement note for DFlash 2, GPU-optimized quantizations, quality-vs-TPS charts on RTX 5090 with links to additional plots, and a model table beginning with GPU-1 IQ2_XXS at 2.5 bits/weight.

EstimatedRepository opened Aug 18, 2026Source checked 9/24/2026Version: 3fdfbd9b
LOCALRENTED GPUOPEN WEIGHTS
Freshness 80 out of 100. Repository age: 58 days old, Aug 18, 2026. Measures age, not quality.
Popularity 80 out of 100. 1,556,746 downloads in 30 days; 173 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 23 of 225. Ranked model: qwen3.8-27b. Original model ranking, not a benchmark of this package. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.
Category rankings & sources

Each position belongs to a separate Arena category. These are human preference rankings—not hardware recommendations. We do not combine the categories into one score.

Text#23of 225 open models
qwen3.8-27balibabaLicense: Apache 2.0

Original model ranking. This does not benchmark the selected quantization or package.

Export dated Oct 13, 2026Checked: Oct 15, 2026Overall board: #100
View official Text board
Vision#9of 49 open models
qwen3.8-27balibabaLicense: Apache 2.0

Original model ranking. This does not benchmark the selected quantization or package.

Export dated Oct 9, 2026Checked: Oct 15, 2026Overall board: #61
View official Vision board
Web coding#10of 55 open models
qwen3.8-27balibabaLicense: Apache 2.0

Original model ranking. This does not benchmark the selected quantization or package.

Export dated Oct 13, 2026Checked: Oct 15, 2026Overall board: #29
View official Web coding board
Agents#11of 18 open models
Qwen 3.8 27BalibabaLicense: Apache 2.0

Original model ranking. This does not benchmark the selected quantization or package.

Export dated Oct 14, 2026Checked: Oct 15, 2026Overall board: #40
View official Agents board

Rankings reflect the dated export; live Arena boards can change. Open-source positions use Arena’s open-model filter. The overall position also includes the other models on that category board. Availability of weights and license terms still need to be checked separately.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source
Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source
Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Architecture
unknown
License
apache-2.0
Disk space
12.2 GB
Software
llama.cpp
View the model source
MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

  • Image-and-text inputs through an image-text-to-text pipeline.
  • Quantized local inference in GGUF-supported tools such as llama.cpp.
  • Vision-capable workflows in llama.cpp when the vision projector is auto-downloaded.
  • Instruction-following tasks in instruct mode, as evaluated by the model card's benchmark suite.
  • Thinking-mode agentic tasks or tool use, as evaluated by the model card's benchmark suite.

Tradeoffs

  • The supplied source does not include full model card data; the officialModelCard field is truncated mid-table.
  • No independent testing, benchmarking, or verification of the model's quality, speed, or compatibility is claimed here.
  • DFlash 2 is stated to require llama.cpp build b10658 (2026-08-27) or newer; other builds are not confirmed by the source.
  • Performance, quality-vs-TPS, and benchmark results are only as stated in the model card and are not independently verified.
  • Exact quantization variants, model sizes, token limits, and full hardware requirements beyond the supplied snippets are not known from the source.

Ways to run it

llama.cpp · Windows, macOS, Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

llama-server -hf byteshape/Qwen3.8-27B-GGUF:Qwen3.8-27B-IQ4_XS-3.84bpw -hfd incoai/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M --spec-type draft-dflash --spec-draft-n-max 7 --no-mmproj
Official instructions

Explore its uses

GGUFIMAGE-TEXT-TO-TEXT

Keep exploring

Text
Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.
Popularity 90 out of 100. 4,849,199 downloads in 30 days; 2,697 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
MODEL SIZE27.36B
LOCALRENTED GPU
Released Sep 17, 2026
Text
DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,238,583 downloads in 30 days; 4,519 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3
LOCALRENTED GPU
Repository opened Sep 10, 2026
Text
Qwen

Qwen3 8B

Qwen3-8B is a causal language model from the Qwen series, developed by the Qwen team. It is an 8.2B parameter model (6.95B non-embedding) with 36 layers and grouped-query attention (32 query heads, 8 key/value heads). The model supports text generation and is designed for both thinking and non-thinking modes within a single model. It has a native context length of 32,768 tokens, extendable to 131,072 tokens with YaRN. The model card highlights advancements in reasoning, instruction-following, agent capabilities, and multilingual support (100+ languages). It is licensed under Apache-2.0 and built on Qwen/Qwen3-8B-Base.

Freshness 13 out of 100. Repository age: 536 days old, Apr 27, 2025. Measures age, not quality.
Popularity 93 out of 100. 9,578,964 downloads in 30 days; 2,119 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
MODEL SIZE8.2B
LOCALRENTED GPU
Repository opened Apr 27, 2025