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

Anbeeld/gemma-4-26B-A4B-it-DFlash-GGUF overview

Gemma 4 26B A4B IT DFlash GGUF llama.cpp quantizations of z lab DFlash draft model https://huggingface.co/z lab/gemma 4 26B A4B it DFlash for Gemma 4 26B A4B h…

transformersggufqwen3safetensorsdflashspeculative-decodingblock-diffusiondraft-modelefficiencyqwengemmadiffusion-language-modeltext-generationarxiv:2602.06036license:apache-2.0text-generation-inferenceendpoints_compatibleregion:usbase_model:z-lab/gemma-4-26B-A4B-it-DFlashbase_model:quantized:z-lab/gemma-4-26B-A4B-it-DFlashconversational

Runs locally from ~166.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
1,896
Likes
2
Pipeline
text-generation
Author

Repository Files & Downloads

7 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
gemma4-26b-a4b-it-dflash-Q2_K.ggufGGUFQ2_K166.1 MBDownload
gemma4-26b-a4b-it-dflash-Q3_K_M.ggufGGUFQ3_K_M211.1 MBDownload
gemma4-26b-a4b-it-dflash-Q4_K_M.ggufGGUFQ4_K_M254.9 MBDownload
gemma4-26b-a4b-it-dflash-Q5_K_M.ggufGGUFQ5_K_M301.6 MBDownload
gemma4-26b-a4b-it-dflash-Q6_K.ggufGGUFQ6_K351.3 MBDownload
gemma4-26b-a4b-it-dflash-Q8_0.ggufGGUFQ8_0450.5 MBDownload
gemma4-26b-a4b-it-dflash-bf16.ggufGGUFBF16834.7 MBDownload

Model Details

Model IDAnbeeld/gemma-4-26B-A4B-it-DFlash-GGUF
AuthorAnbeeld
Pipelinetext-generation
License
Base modelz-lab/gemma-4-26B-A4B-it-DFlash
Last modified2026-07-19T02:19:48.000Z

Model README

---

base_model: z-lab/gemma-4-26B-A4B-it-DFlash

tags:

  • transformers
  • safetensors
  • qwen3
  • dflash
  • speculative-decoding
  • block-diffusion
  • draft-model
  • efficiency
  • qwen
  • gemma
  • diffusion-language-model
  • text-generation
  • arxiv:2602.06036
  • license:apache-2.0
  • text-generation-inference
  • endpoints_compatible
  • region:us

---

Gemma 4 26B A4B IT DFlash GGUF

llama.cpp quantizations of z-lab DFlash draft model for Gemma 4 26B A4B.

Run Anbeeld/gemma-4-26B-A4B-it-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