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

giocom/Qwen3.6-35B-A3B-DFlash-GGUF overview

Qwen3.6 35B A3B DFlash

transformersggufdflashspeculative-decodingspeculative-decoding-draftblock-diffusiondraft-modeldiffusion-language-modelefficiencyqwenqwen3qwen3.6sglangtext-generationbase_model:z-lab/Qwen3.6-35B-A3B-DFlashbase_model:quantized:z-lab/Qwen3.6-35B-A3B-DFlashlicense:apache-2.0region:us

Runs locally from ~224.8 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
434
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Qwen3.6-35B-A3B-DFlash-BF16.ggufGGUFBF16746.5 MBDownload
Qwen3.6-35B-A3B-DFlash-Q4_K_M.ggufGGUFQ4_K_M224.8 MBDownload
Qwen3.6-35B-A3B-DFlash-Q8_0.ggufGGUFQ8_0401.5 MBDownload

Model Details

Model IDgiocom/Qwen3.6-35B-A3B-DFlash-GGUF
Authorgiocom
Pipelinetext-generation
Licenseapache-2.0
Base modelz-lab/Qwen3.6-35B-A3B-DFlash
Last modified2026-07-20T00:12:54.000Z

Model README

---

pipeline_tag: text-generation

library_name: transformers

base_model:

  • z-lab/Qwen3.6-35B-A3B-DFlash

license: apache-2.0

inference: false

tags:

  • dflash
  • speculative-decoding
  • speculative-decoding-draft
  • block-diffusion
  • draft-model
  • diffusion-language-model
  • efficiency
  • qwen
  • qwen3
  • qwen3.6
  • sglang

---

Qwen3.6-35B-A3B-DFlash

Run giocom/Qwen3.6-35B-A3B-DFlash-GGUF 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