Jundot/Qwen3.6-27B-oQ8-mtp[!IMPORTANT] This quantization was uploaded on 2026 05 13 and replaces a previous version. If you downloaded this model before this date, please re download for the updated weights. Qwen3.6 27B oQ8 mtp This model was quantized using oQ (oMLX v0.3.9.dev2) mixed precision quantization. Quantization details Model type : qwen3 5 Bits : 8 Group size : 64 Format : MLX safetensors

Qwen3.6-27B-oQ8-mtp

PUBLIC

Mirrored

This quantization was uploaded on 2026-05-13 and replaces a previous version.

Libraries:mlx

imported

huggingface

minio

mlx

safetensors

qwen3_5

quantized

8-bit

region:us

0downloads0likesmlx

Model Card

Edit

[!IMPORTANT] This quantization was uploaded on 2026-05-13 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Qwen3.6-27B-oQ8-mtp

This model was quantized using oQ (oMLX v0.3.9.dev2) mixed-precision quantization.

Quantization details

Model type: qwen3_5
Bits: 8
Group size: 64
Format: MLX safetensors

Inference Providers

This model isn't deployed by any Inference Provider yet. Deploy this model →

Safetensors details

Format

Safetensors

Model size

27B params

Quantization

Quantized

Source

Mirrored from an external registry.

Last synced 6/14/2026

Files

main

17 files · 28 GBHistory

Security scan in progress for 17 files.

main

17 files · 28 GB

.gitattributes1.5 KB

chat_template.jinja7.6 KB

config.json3.8 KB

generation_config.json202 B

merges.txt3.2 MB

model-00001-of-00006.safetensorsLFS4.7 GB

model-00002-of-00006.safetensorsLFS4.7 GB

model-00003-of-00006.safetensorsLFS5.8 GB

model-00004-of-00006.safetensorsLFS4.7 GB

model-00005-of-00006.safetensorsLFS4.7 GB

model-00006-of-00006.safetensorsLFS3.3 GB

model.safetensors.index.json207.2 KB

preprocessor_config.json390 B

README.md506 B

tokenizer_config.json16.3 KB

tokenizer.json12.2 MB

vocab.json6.4 MB

We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy