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

From:

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

Qwen3.5-4B-MTP-4bit

Date: 2026-11-15Commit: ab6f59bSigned: 2DC28CC7B26A283B ✓

Text generation model with 121M parameters. Safetensors weights, 87.4 MB in all. Published by mlx-community under Apache-2.0.

121M params

87.4MBQwen3.5-4B-MTP-4bitsafetensorspermissive

FactsParams121MSize87.4 MBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/Qwen3.5-4B-MTP-4bit
# manifest sha256 8782da05faee… · 87.4 MB · 8 files
$ fw verify ./Qwen3.5-4B-MTP-4bit mlx-community/Qwen3.5-4B-MTP-4bit

From sourceHosted (signed)mlx-community/Qwen3.5-4B-MTP-4bitLast check: 2026-11-15 05:14 UTC

Run at home Get help

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

Quantized of Qwen3.5-4B.

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: 87.4 MB
Weights: 67.9 MB (safetensors)
Parameters: 121M
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/Qwen3.5-4B

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 05:14 UTC	passed

Model card

From the publisher at commit ab6f59b. Shown as plain text with links; images open at the publisher.

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

This repository contains quantized Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.5-4B 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 4B target checkpoint.

Use with mlx-vlm#

uv run mlx_vlm.generate \
  --model Qwen/Qwen3.5-4B \
  --draft-model mlx-community/Qwen3.5-4B-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/Qwen3.5-4B-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 4B
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 Qwen3.5 4B 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/Qwen3.5-4B model card and license terms for model usage constraints.

Files

8 files · 87.4 MBWeights 67.9 MB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 8 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	1.86 KB	331aa2bde049a134b1eadb638552481857cdc71778aa8a6ba4dc2c5d041d0653
config.json	2.66 KB	8722089695f36b94ecbf30d8c8bb8b23fe5e49a54ab77e049ae6d12f56584773
model.safetensors	67.9 MB	4e0466e99be0114e59a91a834aa4c338c98610e402664a662f97d95fb2da4b28
model.safetensors.index.json	1.97 KB	cb6379bf58aa4e404957d7b7e78eda83e8900a2e5cb46477c740ee5714ee9055
tokenizer.json	12.8 MB	5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
tokenizer_config.json	16.7 KB	316230d6a809701f4db5ea8f8fc862bc3a6f3229c937c174e674ff3ca0a64ac8
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
ab6f59bc66 pinned now	2026-11-15 05:14 UTC	8 files · 87.4 MB

Use it

$ fw get mlx-community/Qwen3.5-4B-MTP-4bit
# manifest sha256 8782da05faee… · 87.4 MB · 8 files
$ fw verify ./Qwen3.5-4B-MTP-4bit mlx-community/Qwen3.5-4B-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/Qwen3.5-4B-MTP-4bit.json --dir ./Qwen3.5-4B-MTP-4bit
$ python3 fw.py verify ./Qwen3.5-4B-MTP-4bit ./mlx-community__Qwen3.5-4B-MTP-4bit.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.5-4B-MTP-4bit --revision ab6f59bc6627196c611ab8851638651078170485 --local-dir ./Qwen3.5-4B-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/Qwen3.5-4B-MTP-4bit", revision="ab6f59bc6627196c611ab8851638651078170485")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3.5-4B-MTP-4bit", revision="ab6f59bc6627196c611ab8851638651078170485", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3.5-4B-MTP-4bit --revision ab6f59bc6627196c611ab8851638651078170485

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: 331aa2bde049a134b1eadb638552481857cdc71778aa8a6ba4dc2c5d041d0653
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: Qwen3.5-4B-MTP-4bitDate: 2026-11-15Commit: ab6f59bSigned: 2DC28CC7B26A283B ✓

Upstream: mlx-community/Qwen3.5-4B-MTP-4bit
Pinned commit: ab6f59bc6627196c611ab8851638651078170485
Manifest: Qwen3.5-4B-MTP-4bit.json · .minisig
Manifest sha256: 8782da05faeec1c812c983365ced2a7898519f34f651cca16ec15930b9f73591
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:14 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

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

Source

huggingface.co/mlx-community/Qwen3.5-4B-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

Qwen3.5-4B-MTP-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

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

Use with mlx-vlm#

Model Details#

Intended Use#

Limitations#

Files

Use it

License

Provenance

How to verify

Model tree

Related models