PulseGateIndexCategoriesUpdatesLive intelligence on AI-era software— indexed in the last hour
Coverage—projects tracked
Freshness—newest entry
Cadence—last week average · — today
Index9 markets86 categories
PulseGate

Live intelligence on the AI-era software market — apps, models, agents and infrastructure.

Most of it never reaches an official store. PulseGate maps the whole market — every category, worldwide — and measures how it moves: what’s launching, what’s gaining, what’s going quiet.

FollowGitHubX (Twitter)LinkedIn
Platform
All AppsFull IndexCategoriesIndustry UpdatesData SourcesCoverage RulesGlossaryEmbed Widget
Support
Help CenterSubmit your projectReport an Issue
Company
AboutDimaxiaPress & DataContactPlatform Status
Legal
PrivacyTermsDisclaimer
Dimaxia · Dymaxio s.r.o. · Prague, Czechia · © 2026WatchlistSitemapSystem status
PulseGateQ3Qwen3.6 35B A3B MTP
Visit↗
Skip to content
  1. Index›
  2. Foundation models & chat›
  3. Qwen3.6 35B A3B MTP
← Back to the index
Q3

Qwen3.6 35B A3B MTP

huggingface.co·Infrastructure

A GGUF quantized version of Alibaba's Qwen3.6-35B model using an A3B (active 3B parameters) Mixture-of-Experts architecture and MTP (Medusa-style) speculative decoding. Optimized by Unsloth for efficient local inference.

Open SourceApache-2.0WebCLIAPI
QQwen3.6 35B A3B MTP preview
Visit huggingface.co↗
69.6kstars
6.3kforks
20alternatives
3features
2023since

Overview

3 features

Qwen3.6 35B A3B MTP sits in PulseGate's Foundation models & chat category. It focuses on running large MoE language models locally with reduced memory requirements. It is built as an open-source project for developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.

It is developed by Unsloth, and it first shipped in 2023. Development happens publicly on GitHub with 69.6k stars and 1.5k commits in the last 90 days. The category is crowded — PulseGate's index counts 20 comparable apps. Among its 3 catalogued features are GGUF format, mixture of Experts, and quantized.

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

  • ✓GGUF format
  • ✓Mixture of Experts
  • ✓Quantized
Tags
qwenmixture-of-expertsgguf-quantized
AI capabilities
Multimodal
Inference: LocalWeights: Open

Built with & integrations

Hosting
AWS
AI providers
anthropiclocal_ossgoogle_geminiopenai
Runs on
BrowserCLIAPI-only
Detected from
AWS
x-amz-cf-id header · x-amz-cf-pop header · via header
openai
bgpt- in the HTML
anthropic
bclaude in the HTML · bclaude- in the HTML
local_oss
bollama in the HTML · bllama in the HTML · bvllm in the HTML
google_gemini
bgemini- in the HTML

Trust & compliance

License
Apache-2.0
Verified signals
✓HTTPS✓Open Source✓Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed5 Aug · 08:05 UTC
    unsloth/Qwen3.6-35B-A3B-MTP-GGUF verified against its public source
    Source: PulseGate · Open ↗

Frequently asked questions about Qwen3.6 35B A3B MTP

What does Qwen3.6 35B A3B MTP do?
Qwen3.6 35B A3B MTP focuses on running large MoE language models locally with reduced memory requirements. It is catalogued under Foundation models & chat on PulseGate.
Who is Qwen3.6 35B A3B MTP for?
Qwen3.6 35B A3B MTP is an open-source project built for developers.
Does Qwen3.6 35B A3B MTP have a free plan?
Yes — Qwen3.6 35B A3B MTP is open source under the Apache-2.0 license and free to use.
What platforms does Qwen3.6 35B A3B MTP run on?
Qwen3.6 35B A3B MTP runs on the web, the command line, and API.
Is Qwen3.6 35B A3B MTP still active?
The GitHub repository shows 1.5k commits in the last 90 days.
What projects are similar to Qwen3.6 35B A3B MTP?
Similar projects tracked by PulseGate include Qwen3.5 122B A10B MTP, Qwen3.5 9B MTP, and Qwen3.6 35B A3B APEX MTP.Qwen3.5 122B A10B MTPQwen3.5 9B MTPQwen3.6 35B A3B APEX MTP
Who makes Qwen3.6 35B A3B MTP?
Qwen3.6 35B A3B MTP is developed by Unsloth.
When did Qwen3.6 35B A3B MTP launch?
Qwen3.6 35B A3B MTP first shipped in 2023.

At a glance

Pricing
Open Source
Platforms
Cli · Web
Languages
English
License
Apache-2.0
Built for
developers
Model
Open source
Solves
Running large MoE language models locally with reduced memory requirements.

Registered as

Hugging Face
unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Developer

Unsloth
Community-driven

Open source

Stars
69,590
Forks
6,279
Open issues
1,012
Last commit
5 Aug 2026
Commits 90d
1,516
Contributors
269
Authorship
Community-driven
Default branch
main
Latest release
v0.1.521-beta · 4 Aug 2026

Live coverage

Identity confidence
Medium · 70.4
Indexed
5 Aug 2026
Lifecycle
Alive
Last seen
5 Aug 2026
Identity audit (13)
Slug
unsloth-qwen3-6-35b-a3b-mtp-gguf-huggingface-co
Lifecycle state recorded
5 Aug 2026
Verification state
Indexed for public listing
Listing state
Listed: yes
Index status
Included in index
Latest evidence snapshot
5 Aug 2026
Timeline basis
Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from
Derived from the project's own page and URL.
Category from
Derived from the model's own Hugging Face metadata.
Summary from
Written by a language model from public pages.
Languages from
Detected by a language model from page content.
Last updated
5 Aug 2026
Canonical URL
https://huggingface.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Ship this? Send a correction — no account, and you get a link to follow it.

Similar apps

Closest matches by what these projects do

  • Q1Qwen3.5 122B A10B MTPhuggingface.co
  • Q9Qwen3.5 9B MTPhuggingface.co
  • Q3Qwen3.6 35B A3B APEX MTPhuggingface.co
  • Q4Qwen3.5 4B MTPhuggingface.co
  • Q2Qwen3.6 27B MTPhuggingface.co
  • Q3Qwen3.6 35B A3B NVFP4 MTPhuggingface.co