GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

tooltd/Qwen3.6-27B-AutoRound-GGUF-NoMTP overview

This is a repository of GGUF files without MTP , It is old version before updating MTP re uploaded from sphaela/Qwen3.6 27B AutoRound GGUF https://huggingface.…

ggufauto-roundintelquantizationmultilingualbase_model:Qwen/Qwen3.6-27Bbase_model:quantized:Qwen/Qwen3.6-27Blicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~11.24 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
108
Likes
0
Pipeline
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Qwen3.6-27B-Autoround-Q3_K_L.ggufGGUFQ3_K_L11.24 GBDownload
Qwen3.6-27B-Autoround-Q4_K_M.ggufGGUFQ4_K_M14.41 GBDownload

Model Details

Model IDtooltd/Qwen3.6-27B-AutoRound-GGUF-NoMTP
Authortooltd
Pipeline
Licenseapache-2.0
Base modelQwen/Qwen3.6-27B
Last modified2026-06-26T12:32:09.000Z

Model README

---

license: apache-2.0

language:

  • multilingual

base_model: Qwen/Qwen3.6-27B

tags:

  • auto-round
  • intel
  • gguf
  • quantization

---

This is a repository of GGUF files (without MTP , It is old version before updating MTP) re-uploaded from sphaela/Qwen3.6-27B-AutoRound-GGUF

Qwen3.6-27B GGUF (AutoRound Quantized)

This repository contains GGUF quantized versions of Qwen/Qwen3.6-27B created using Intel's AutoRound quantization method.

About AutoRound

AutoRound is an advanced quantization technique from Intel that aims to minimize accuracy loss through automated rounding optimization. The iterative calibration mode (--enable_alg_ext) runs gradient-based optimization for 200 iterations per block, finding optimal rounding thresholds that minimize reconstruction error.

---

Run tooltd/Qwen3.6-27B-AutoRound-GGUF-NoMTP with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models