CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.6-35B-A3B-MTP-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.6-35B-A3B-MTP-4bit

Date: 2026-11-15Commit: 0295b81Signed: 2DC28CC7B26A283B ✓

Text generation model with 845M parameters. Safetensors weights, 495 MB in all. Published by mlx-community under Apache-2.0.

845M params495MBQwen3.6-35B-A3B-MTP-4bitsafetensorspermissive
FactsParams845MSize495 MBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3.6-35B-A3B-MTP-4bit
# manifest sha256 22007c984f5f… · 495 MB · 8 files
$ fw verify ./Qwen3.6-35B-A3B-MTP-4bit mlx-community/Qwen3.6-35B-A3B-MTP-4bit
From sourceHosted (signed)mlx-community/Qwen3.6-35B-A3B-MTP-4bitLast check: 2026-11-15 05:07 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of Qwen3.6-35B-A3B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
495 MB
Weights
475 MB (safetensors)
Parameters
845M
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
8, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.6-35B-A3B

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:07 UTCpassed

Model card

From the publisher at commit 0295b81. Shown as plain text with links; images open at the publisher.

Qwen3.6-35B-A3B-MTP-4bit#

This repository contains quantized Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.6-35B-A3B for use with mlx-vlm speculative decoding.

This is not a standalone chat or text-generation model. Load it as the draft model alongside a compatible Qwen3.6 35B-A3B target checkpoint.

Use with mlx-vlm#

uv run mlx_vlm.generate \
  --model Qwen/Qwen3.6-35B-A3B \
  --draft-model mlx-community/Qwen3.6-35B-A3B-MTP-4bit \
  --prompt "Hi, how are you?" \
  --max-tokens 256 \
  --enable-thinking

For local weights:

uv run mlx_vlm.generate \
  --model /path/to/target-model \
  --draft-model /path/to/Qwen3.6-35B-A3B-mtp-4bit \
  --prompt "Hi, how are you?" \
  --max-tokens 256 \
  --enable-thinking

Model Details#

  • Model type: qwen3_5_mtp
  • MTP block size: 2
  • Target architecture: Qwen3.6 35B-A3B
  • Precision: MLX affine 4-bit, group size 64
  • Runtime: MLX / mlx-vlm
  • Format: Safetensors with MLX-compatible config and tokenizer files

The stored tensors use MLX affine quantization as described in config.json.

Intended Use#

Use this repo only as a speculative decoding drafter for compatible Qwen3.6 35B-A3B checkpoints. The target model verifies drafted tokens, while this MTP model proposes candidate tokens per decoding step.

Limitations#

This checkpoint requires runtime support for Qwen MTP draft models in mlx-vlm. Standard standalone generation through generic Transformers APIs is not expected to work with this repository by itself.

Please refer to the upstream Qwen/Qwen3.6-35B-A3B model card and license terms for model usage constraints.

Files

8 files · 495 MBWeights 475 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 8 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.92 KBc2eb3bd66a5fd68f6611f4a219d1c781f8d250ad1ce9c819309a79fd3b655810
config.json3.18 KB7b38a336fa246a285ee23cc990351989bf2ee6c040506a2b793ee24e463f35a7
model.safetensors475 MB77fbc6594cdd830cae89e0b693f18278dd0a7a7c5749fd33d4bc5817dbb91bad
model.safetensors.index.json3.13 KB00e220ddb21ceeb6290a3a1161f97339c553f3d27fc4319900a96edb5cfae74c
tokenizer.json12.8 MB5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
tokenizer_config.json16.7 KB5186f0defcd7f232382c7f0aebcd2252d073bb921ab240e407b7ae8745d2b29b
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0295b81421 pinned now2026-11-15 05:07 UTC8 files · 495 MB

Use it

$ fw get mlx-community/Qwen3.6-35B-A3B-MTP-4bit
# manifest sha256 22007c984f5f… · 495 MB · 8 files
$ fw verify ./Qwen3.6-35B-A3B-MTP-4bit mlx-community/Qwen3.6-35B-A3B-MTP-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3.6-35B-A3B-MTP-4bit.json --dir ./Qwen3.6-35B-A3B-MTP-4bit $ python3 fw.py verify ./Qwen3.6-35B-A3B-MTP-4bit ./mlx-community__Qwen3.6-35B-A3B-MTP-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.6-35B-A3B-MTP-4bit --revision 0295b81421bf4d0fccca9a7c0fcfb1418dda3516 --local-dir ./Qwen3.6-35B-A3B-MTP-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("mlx-community/Qwen3.6-35B-A3B-MTP-4bit", revision="0295b81421bf4d0fccca9a7c0fcfb1418dda3516") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3.6-35B-A3B-MTP-4bit", revision="0295b81421bf4d0fccca9a7c0fcfb1418dda3516", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3.6-35B-A3B-MTP-4bit --revision 0295b81421bf4d0fccca9a7c0fcfb1418dda3516
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
c2eb3bd66a5fd68f6611f4a219d1c781f8d250ad1ce9c819309a79fd3b655810
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject: Qwen3.6-35B-A3B-MTP-4bitDate: 2026-11-15Commit: 0295b81Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3.6-35B-A3B-MTP-4bit
Pinned commit
0295b81421bf4d0fccca9a7c0fcfb1418dda3516
Manifest
Qwen3.6-35B-A3B-MTP-4bit.json · .minisig
Manifest sha256
22007c984f5fc07b3b1f37372f3b80d8b758963b5c4b672562484509f0595245
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:07 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.6-35B-A3B-MTP-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.6-35B-A3B-MTP-4bit.json.minisig $ minisign -Vm Qwen3.6-35B-A3B-MTP-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen3.6-35B-A3B · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.6-35B-A3B-MTP-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.6-35B-A3B-MTP-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3.6-35B-A3B-MTP-4bit

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF