Store › model › Embeddings

Qwen3.5-9B-DFlash-GGUF

Name: Qwen3.5-9B-DFlash-GGUF
Author: Anbeeld

by Anbeeld · source Hugging Face · updated 2026-08-29

apache-2.0730 MB~2 GB RAMsource aliveunlabeled

GGUF quantizations of z-lab DFlash draft model for Qwen 3.5 9B.

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:Anbeeld/Qwen3.5-9B-DFlash-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/Anbeeld/Qwen3.5-9B-DFlash-GGUF
License: apache-2.0
Requirements: about 2 GB of RAM, 730 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
Tags: transformers gguf qwen3 feature-extraction safetensors dflash speculative-decoding speculative-decoding-draft block-diffusion draft-model diffusion-language-model efficiency qwen qwen3.5 sglang text-generation

Numbers

4,712 downloads on Hugging Face
5 likes
license apache-2.0
0.7 GB for qwen35-9b-dflash-Q4_K_M.gguf
327,838 npm downloads a week for node-llama-cpp
latest node-llama-cpp@3.22.1

Numbers as of 2026-10-02 20:59 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`qwen35-9b-dflash-Q2_K.gguf`	Q2_K	460 MB
`qwen35-9b-dflash-Q3_K_M.gguf`	Q3_K_M	595 MB
`qwen35-9b-dflash-Q4_K_M.gguf`	Q4_K_M	730 MB
`qwen35-9b-dflash-Q5_K_M.gguf`	Q5_K_M	871 MB
`qwen35-9b-dflash-Q6_K.gguf`	Q6_K	1021 MB
`qwen35-9b-dflash-Q8_0.gguf`	Q8_0	1.3 GB
`qwen35-9b-dflash-bf16.gguf`	BF16	2.4 GB

From the source README

Qwen 3.5 9B DFlash GGUF

GGUF quantizations of z-lab DFlash draft model for Qwen 3.5 9B.

Use with BeeLlama.cpp, a llama.cpp fork with advanced quantization features.

Qwen3.5-9B-DFlash

Paper | Github | Blog

This DFlash draft model is a joint retrain from Z-Lab and Modal, trained with 40k sequence length and sliding-window attention for improved long-context performance. It is mirrored across the following Hugging Face repositories:

`z-lab/Qwen3.5-9B-DFlash`
`modal-labs/Qwen3.5-9B-DFlash`

This repository contains a DFlash draft model for `Qwen/Qwen3.5-9B`. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server.

DFlash uses a lightweight block diffusion draft model to propose multiple tokens in parallel. The target model verifies those proposals, improving serving throughput while preserving the target model's output distribution.

Quick Start

Installation

SGLang

Card id model:hf:Anbeeld/Qwen3.5-9B-DFlash-GGUF · collected 2026-10-02 20:59 UTC · JSON