TheHouseOfTheDude/Qwen3.6-27B-INT8Qwen3.6 27B INT8 — PTQ Quantized (W8A16) Overview Post Training Quantized (PTQ) version of Qwen/Qwen3.6 27B. No calibration dataset One shot quantization Uses llmcompressor Quantization Scheme: W8A16 Weights: INT8 Activations: FP16/BF16 Targets: Linear layers only Ignored: lm head visual linear attn mtp KLD Results: Mean KLD: 0.009441 Usage Notes Requires vLLM Not for vanilla Transformers

Qwen3.6-27B-INT8

PUBLIC

Mirrored

Qwen3.6-27B-INT8 — PTQ Quantized (W8A16)

Tasks:image-text-to-textLibraries:vllmLicense:other

imported

huggingface

vllm

safetensors

qwen3_5

text-generation

image-generation

conversational

compressed-tensors

PTQ

w8a16

quantized

image-text-to-text

base_model:Qwen/Qwen3.6-27B

base_model:quantized:Qwen/Qwen3.6-27B

license:other

region:us

16.1Kdownloads9likesvllmLicense:other

Model Card

Edit

Qwen3.6-27B-INT8 — PTQ Quantized (W8A16)

Overview

Post-Training Quantized (PTQ) version of Qwen/Qwen3.6-27B.

No calibration dataset
One-shot quantization
Uses llmcompressor

Quantization

Scheme: W8A16
Weights: INT8
Activations: FP16/BF16
Targets: Linear layers only

Ignored:

lm_head
visual
linear_attn
mtp

KLD Results:

Mean KLD: 0.009441

Usage

vllm serve TheHouseOfTheDude/Qwen3.6-27B-INT8 \
  --quantization compressed-tensors

Notes

Requires vLLM
Not for vanilla Transformers

Inference Providers

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

Model details

Model size

27B params

Quantization

Quantized

Tasks

image-text-to-text

Source

Mirrored from an external registry.

Last synced 7/29/2026

Model tree for TheHouseOfTheDude/Qwen3.6-27B-INT8

Base model

Qwen/Qwen3.6-27B

Commit History

No commits available

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