alt.freeweights.qwen / Qwen3.5-9B-MTP-4bit

From:

mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-9B-MTP-4bit

Date: 2026-11-15Commit: 222dfd2Signed: 2DC28CC7B26A283B ✓

Text generation model with 243M parameters. Safetensors weights, 164 MB in all. Published by mlx-community under Apache-2.0.

243M params

164MBQwen3.5-9B-MTP-4bitsafetensorspermissive

FactsParams243MSize164 MBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/Qwen3.5-9B-MTP-4bit
# manifest sha256 64bec8a13f17… · 164 MB · 9 files
$ fw verify ./Qwen3.5-9B-MTP-4bit mlx-community/Qwen3.5-9B-MTP-4bit

From sourceHosted (signed)mlx-community/Qwen3.5-9B-MTP-4bitLast check: 2026-11-15 05:08 UTC

Run at home Get help

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

Quantized of Qwen3.5-9B.

Works with

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 164 MB
Weights: 137 MB (safetensors)
Parameters: 243M
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 9, each with a sha256
Publisher: mlx-community
Added: 2026-11-15
Section: alt.freeweights.qwen

Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.5-9B

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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:08 UTC	passed

Model card

From the publisher at commit 222dfd2. Shown as plain text with links; images open at the publisher.

Qwen3.5-9B-MTP-4bit#

This repository contains Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.5-9B 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 Qwen3.5 9B target checkpoint.

Use with mlx-vlm#

uv run mlx_vlm.generate \
  --model mlx-community/Qwen3.5-9B-5bit \
  --draft-model mlx-community/Qwen3.5-9B-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/Qwen3.5-9B-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: Qwen3.5 9B
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 4-bit quantization as described in config.json.

Intended Use#

Use this repo only as a speculative decoding drafter for compatible Qwen3.5 9B 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/DeepSeek 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/Qwen3.5-9B model card and license terms for model usage constraints.

Files

9 files · 164 MBWeights 137 MB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 9 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	1.88 KB	dc6da4f4bb7ff1d056978d3cf58c6e8c97d2f24a9b7e6c2bf76ef28f13e968fc
chat_template.jinja	7.76 KB	a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715
config.json	2.65 KB	1e9c8d97dd6c2c4621f047a39871a99515a1424141607ce79d6de9ce57811164
model.safetensors	137 MB	ff2f9298bb78a0f015a9998fecda6b5d40c2995d9ecd55e65a206ee5e6d6f897
model.safetensors.index.json	1.97 KB	398fcc545ccbb7ab06a5d4c2a0d9c1122d8f8900115fd307064dbb57dbfaa2ae
tokenizer.json	20.0 MB	06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
tokenizer_config.json	1.09 KB	4cf9d39d3e1c9ce0143dc9740951a63e83661298155648c99a0e1721734086f8
vocab.json	6.72 MB	ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
222dfd2c23 pinned now	2026-11-15 05:08 UTC	9 files · 164 MB

Use it

$ fw get mlx-community/Qwen3.5-9B-MTP-4bit
# manifest sha256 64bec8a13f17… · 164 MB · 9 files
$ fw verify ./Qwen3.5-9B-MTP-4bit mlx-community/Qwen3.5-9B-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/Qwen3.5-9B-MTP-4bit.json --dir ./Qwen3.5-9B-MTP-4bit
$ python3 fw.py verify ./Qwen3.5-9B-MTP-4bit ./mlx-community__Qwen3.5-9B-MTP-4bit.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.5-9B-MTP-4bit --revision 222dfd2c23fc9518d7b817e4f8e0cb0571787489 --local-dir ./Qwen3.5-9B-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/Qwen3.5-9B-MTP-4bit", revision="222dfd2c23fc9518d7b817e4f8e0cb0571787489")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3.5-9B-MTP-4bit", revision="222dfd2c23fc9518d7b817e4f8e0cb0571787489", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3.5-9B-MTP-4bit --revision 222dfd2c23fc9518d7b817e4f8e0cb0571787489

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: dc6da4f4bb7ff1d056978d3cf58c6e8c97d2f24a9b7e6c2bf76ef28f13e968fc
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: Qwen3.5-9B-MTP-4bitDate: 2026-11-15Commit: 222dfd2Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/Qwen3.5-9B-MTP-4bit
Pinned commit: 222dfd2c23fc9518d7b817e4f8e0cb0571787489
Manifest: Qwen3.5-9B-MTP-4bit.json · .minisig
Manifest sha256: 64bec8a13f17135f1d2da470b977a01bb973e99418df223da6374689bf8f993b
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:08 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-9B-MTP-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-9B-MTP-4bit.json.minisig
$ minisign -Vm Qwen3.5-9B-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/Qwen3.5-9B · 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/Qwen3.5-9B-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. Qwen3.5-9B-MTP-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/Qwen3.5-9B-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

Qwen3.5-9B-MTP-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

Qwen3.5-9B-MTP-4bit#

Use with mlx-vlm#

Model Details#

Intended Use#

Limitations#

Files

Use it

License

Provenance

How to verify

Model tree

Related models