Skip to content
Back to the index

Qwen3.6 35B A3B DFlash

huggingface.coInfrastructure

PulseGate's liveness check found it on 14 Sep 2026; it is registered on Hugging Face and has been in the index since 21 Jul 2026. How this is checked

Qwen3.6-35B-A3B-DFlash is a distilled and optimized variant of the Qwen3 series that uses block diffusion and speculative decoding techniques to accelerate text generation. It is distributed as open weights on Hugging Face and can be used with the Transformers library or SGLang for local or self-hosted inference. The model is intended for developers seeking faster inference without sacrificing much quality from the base Qwen3.6 model.

Inferred · not functionally tested

Open SourceMITWebCLIAPISelf-hosted
Qwen3.6 35B A3B DFlash preview
Visit huggingface.co
5.5kstars
395forks
25alternatives
5features
2026since

Overview

5 features

Purpose: Running large language models with high latency and computational cost during inference.

Inferred · not functionally tested

Audience: developers

Inferred · not functionally tested

Functions: Unknown

Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI, WEB · deployment: browser, cli, api_only, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: huggingface.co. These links do not verify the individual claims.

In the Quantised & converted weights space, Qwen3.6 35B A3B DFlash takes a focused approach. Inferred · not functionally tested: It focuses on running large language models with high latency and computational cost during inference. Inferred · not functionally tested: It is built as an open-source project for developers. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the web, the command line, and API, and it can be self-hosted.

It is developed by Z Lab, and it first shipped in 2026. The project is developed in the open on GitHub with 5.5k stars and 10 commits in the last 90 days. The category is crowded — PulseGate's index counts 25 comparable projects. Inferred · not functionally tested: Key capabilities include Text Generation, Speculative Decoding, and Block Diffusion. Inferred · not functionally tested: Catalogued interfaces include a public API.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Text Generation
  • Speculative Decoding
  • Block Diffusion
  • Transformers Compatible
  • Custom Code

Topics: Inferred · not functionally tested

Tags
speculative-decodingdraft-modelblock-diffusionqwen3text-generation
AI capabilities
Text
Inference: LocalWeights: Open

JSON profile · Text profile · Access guide

Built with & integrations

Hosting
AWS
AI providers
local_oss
Connectors
API
Runs on
BrowserCLIAPI-onlySelf-hosted
Detected from
AWS
x-amz-cf-id header · x-amz-cf-pop header · via header
local_oss
bollama in the HTML · bllama in the HTML · bvllm in the HTML

Trust & compliance

License
MIT
Public signals
HTTPSPrivacy PolicyTerms of ServiceOpen SourceFree tierActive maintenance
Legal
Privacy Policy Terms of Service

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed21 Jul · 17:09 UTC
    z-lab/Qwen3.6-35B-A3B-DFlash seen via Hugging Face Enumerator
    Source: Hugging Face Enumerator · Open

Frequently asked questions about Qwen3.6 35B A3B DFlash

What does Qwen3.6 35B A3B DFlash do?
Inferred · not functionally tested: Qwen3.6 35B A3B DFlash focuses on running large language models with high latency and computational cost during inference. It is catalogued under Quantised & converted weights on PulseGate.
Who is Qwen3.6 35B A3B DFlash for?
Inferred · not functionally tested: Qwen3.6 35B A3B DFlash is an open-source project built for developers.
Does Qwen3.6 35B A3B DFlash have a free plan?
Basis unknown · not verified: Yes — Qwen3.6 35B A3B DFlash is open source under the MIT license and free to use.
What platforms does Qwen3.6 35B A3B DFlash run on?
Basis unknown · not verified: Qwen3.6 35B A3B DFlash runs on the web, the command line, and API. It can also be self-hosted.
Is Qwen3.6 35B A3B DFlash still active?
PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 10 commits in the last 90 days.
What projects are similar to Qwen3.6 35B A3B DFlash?
Similar projects tracked by PulseGate include Qwen3.6 27B DFlash, Qwen3.5 27B DFlash, and Qwen3 8B DFlash B16.Qwen3.6 27B DFlashQwen3.5 27B DFlashQwen3 8B DFlash B16
Who develops Qwen3.6 35B A3B DFlash?
Qwen3.6 35B A3B DFlash is developed by Z Lab.
When did Qwen3.6 35B A3B DFlash launch?
Qwen3.6 35B A3B DFlash first shipped in 2026.

Similar projects

Closest matches by what these projects do