Skip to page content
SAVRN
Search Plan a project

Open-weight model · Image and text to text

Qwen3.8-27B-6bit-MLX

by Timothy Chia timothyckl/Qwen3.8-27B-6bit-MLX

Qwen3.8-27B-6bit-MLX is an open-weight model for image and text to text from Timothy Chia, released under Apache License 2.0. It has 27.4B parameters and a 262,144-token context. At 16-bit it needs about 65.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.

A 6-bit affine MLX quantization of Qwen/Qwen3.8-27B, using a group size of 64. See the base model card for model details, intended uses, and limitations.

Parameters27.4B
Context262,144
Weights22.8 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve Qwen3.8-27B-6bit-MLX (27.4B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 54.7 GB 65.7 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 27.4 GB 32.8 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 13.7 GB 16.4 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 18, 2026.

Qwen3.8-27B-6bit-MLX on every accelerator the SAVRN Index prices, at every precision

Model Card

By Timothy Chia, published under apache-2.0, revision c7016f6d34f2.

A 6-bit affine MLX quantization of Qwen/Qwen3.8-27B, using a group size of 64. See the base model card for model details, intended uses, and limitations.

Read Timothy Chia's full model card

A 6-bit affine MLX quantization of Qwen/Qwen3.8-27B, using a group size of 64.

Usage

pip install -U mlx-vlm
mlx_vlm.generate --model timothyckl/Qwen3.8-27B-6bit-MLX --prompt "Hello!"

See the base model card for model details, intended uses, and limitations.

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
timothyckl/Qwen3.8-27B-6bit-MLX
Publisher
Timothy Chia
Task
Image and text to text
Modality
Image and text
Library
mlx
Parameters
27.4B parameters
Languages
mlx, mlx-vlm
Revision
c7016f6d34f276cfbf0da24cb1f86fe8e7706da3
First published
2026-09-28
Last updated
2026-09-28

Files and Weights

17 files, 22.8 GB in total. The weights are 5 files totalling 22.8 GB in safetensors.

Weights5 files · 22.8 GB
Configuration6 files · 225.2 KB
Tokenizer3 files · 26.7 MB
Documentation1 file · 530 B
Other1 file · 9.0 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00005.safetensorsWeights5.4 GB f32d348378ad
model-00002-of-00005.safetensorsWeights5.3 GB fc5b13b82c16
model-00003-of-00005.safetensorsWeights5.3 GB 0dbbf089bd53
model-00004-of-00005.safetensorsWeights5.3 GB 3ff253fa6838
model-00005-of-00005.safetensorsWeights1.4 GB 070a91acd522
config.jsonConfiguration4.9 KB —
generation_config.jsonConfiguration202 B —
model.safetensors.index.jsonConfiguration218.3 KB —
preprocessor_config.jsonConfiguration390 B —
processor_config.jsonConfiguration991 B —
video_preprocessor_config.jsonConfiguration385 B —
README.mdDocumentation530 B —
chat_template.jinjaOther9.0 KB —
.gitattributesRepository1.6 KB —
tokenizer.jsonTokenizer20.0 MB 06b9509352d2
tokenizer_config.jsonTokenizer1.2 KB —
vocab.jsonTokenizer6.7 MB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
22.8 GB
Download from Timothy Chia

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

Built From

Memory Requirements

PrecisionWeights in memory
As published22.8 GB
16-bit54.7 GB
8-bit27.4 GB
4-bit13.7 GB

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

Questions About Qwen3.8-27B-6bit-MLX

How much GPU memory does Qwen3.8-27B-6bit-MLX need?

About 65.7 GB at 16-bit and 16.4 GB at 4-bit: the weights (27.4B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen3.8-27B-6bit-MLX 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-6bit-MLX commercially?

Yes. Qwen3.8-27B-6bit-MLX 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-6bit-MLX'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-MLX-4bit

LM Studio Community

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 4-bit quantized version of Qwen3.8-27B using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 27.4B parameters 262,144 tokens transformers
View model

Model · Image and text to text

Qwen3.8-27B-MLX-8bit

LM Studio Community

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 8-bit quantized version of Qwen3.8-27B using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 27.4B parameters 262,144 tokens transformers
View model

Model · Image and text to text

Qwen3.8-27B-MLX-6bit

LM Studio Community

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 6-bit quantized version of Qwen3.8-27B using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 27.4B parameters 262,144 tokens transformers
View model

Model · Image and text to text

Qwen3.8-27B-MLX-5bit

LM Studio Community

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 5-bit quantized version of Qwen3.8-27B using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 27.4B parameters 262,144 tokens transformers
View model

Model · Image and text to text

openthai2.0-qwen3.8-27b-MLX-4bit

iApp Technology

MLX 4-bit quantization (mlx-vlm) of for Apple silicon. Vision included. ~16 GB — runs on 24 GB+ unified memory. pip install mlx-vlm python -m mlxvlm generate --model iapp/openthai2.0-qwen3.8-27b-MLX-4bit \ --image document.jpg --prompt "อ่านข้อความในเอกสารนี้ทั้งหมด" --max-tokens 8192 Notes: the MTP draft head is not included (mlx-vlm has no drafter support for this architecture yet). Under TensorFold (below), drafting comes from z-lab's DFlash2 drafter TensorFold serves this checkpoint as published, images included, through an OpenAI-compatible API (/v1/chat/completions, /v1/responses, /v1/messages). It runs on Apple silicon and on NVIDIA GPUs with compute capability 8.9+: RTX 40/50…

Open weights apache-2.0 27.4B parameters 262,144 tokens mlx
View model

Qwen3.5-KETI-HAECHI-27B is a multimodal model derived from Qwen/Qwen3.5-27B. It was developed Korean OCR, and improving tool calling and multi-step, stateful agent execution. Alongside these goals, the model preserves broad multimodal, language, and coding capabilities from the base model. heritage objects, answers questions grounded in heritage images, and reads Korean text from signs, scenes, rendered text, and public documents. - Tool calling and long-horizon task execution: selects and calls tools, carries information across multiple turns, tracks changing state, and works toward an end-to-end goal over several steps. follows Korean and English instructions, and performs visual…

Open weights apache-2.0 27.4B parameters 262,144 tokens transformers
View model