CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / DeepSeek-V4-Pro-Qwen3.5-9B-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

DeepSeek-V4-Pro-Qwen3.5-9B-8bit

Date: 2026-11-15Commit: 93b502eSigned: 2DC28CC7B26A283B ✓

Image text to text model with 9.4B parameters. Safetensors weights, 10.4 GB in all. Published by mlx-community under Apache-2.0.

9.4B params10.4GBDeepSeek-V4-Pro-Qwen3.5-9B-8bitsafetensorspermissive
FactsParams9.4BSize10.4 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit
# manifest sha256 f46094ae874b… · 10.4 GB · 13 files
$ fw verify ./DeepSeek-V4-Pro-Qwen3.5-9B-8bit mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit
From sourceHosted (signed)mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bitLast check: 2026-11-15 05:11 UTC
Run at homeGet help

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

Quantized of DeepSeek-V4-Pro-Qwen3.5-9B.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
10.4 GB
Weights
10.4 GB (safetensors)
Parameters
9.4B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
13, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Jackrong/DeepSeek-V4-Pro-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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:11 UTCpassed

Model card

From the publisher at commit 93b502e. Shown as plain text with links; images open at the publisher.

mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit#

This model mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit was converted to MLX format from Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B using mlx-vlm version 0.4.4.

This is a 8bit MLX quantized conversion. It keeps the source model's chat template and multimodal processor configuration for text/coding, image, and video-style inputs. The language model weights were quantized with MLX 8-bit affine quantization; the multimodal vision components are preserved for image/video inputs.

Refer to the original model card for model details, license, and intended use.

Use with mlx#

pip install -U mlx-vlm
Image input#
python -m mlx_vlm.generate \
  --model mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit \
  --max-tokens 512 \
  --temperature 0.0 \
  --prompt "Describe this image." \
  --image <path_to_image>
Text / coding input#
python -m mlx_vlm.generate \
  --model mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit \
  --max-tokens 512 \
  --temperature 0.2 \
  --prompt "Write a Python function that parses a JSONL file and counts records by label."

Notes#

  • This is a 8bit MLX quantized version of Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B.
  • The model is intended for Apple Silicon inference with MLX.
  • For multimodal usage, prefer mlx-vlm rather than plain mlx-lm.
  • License: Apache 2.0, inherited from the source model metadata.

Conversion#

mlx_vlm.convert \
  --hf-path Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B \
  --mlx-path DeepSeek-V4-Pro-Qwen3.5-9B-8bit \
  --quantize \
  --q-bits 8 \
  --q-group-size 64 \
  --q-mode affine

Files

13 files · 10.4 GBWeights 10.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.17 KB850f1005a5908c8224ba461784536287e578c84459c3fbbe1ded949806d585a2
chat_template.jinja8.74 KBf7e41c826a3eea86dbd6ed2e204f0fc03262fcf720144e1dbb9b6d3e44e333a1
config.json3.64 KB1d44f6600dab889e183276ff310954481206127e9bde651ab0a72ac4a50a3e93
configuration.json58 Bc1b09db419119513247e9b8b912c4b9897106c9b20c6cada7e107d993c5435eb
model-00001-of-00002.safetensors5.34 GBe2989945e239fadf5a84a3d9c4af050bfc2fd573277a86345c3f4185bdd9f66e
model-00002-of-00002.safetensors5.09 GB5f71a31108e71b88e537da0782299c0cc80207958bbd501040e42a017f75c6ec
model.safetensors.index.json124 KB87d95b037f57d101448b262059b7d28d65d55f60231100cdb1827d7cd44202cd
preprocessor_config.json391 B5102cc0567b75a34738c5af8e547c00b1faca4ca63c60b1b79acd0423af0ef43
processor_config.json1.30 KB01562eddd6f9e9ec4bc31656a3b7055284cafbf889acc6c4348dca431ae31f68
tokenizer.json20.0 MB06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
tokenizer_config.json16.2 KB3077139e4d149cc5959884e4f894ffb71dc84495ec2e66840764f3c59411b5da
video_preprocessor_config.json386 B00bd47a5eaaf8760744a12658cd99ba168b818edc4c0a983b90157289c8e546a
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
93b502eb9e pinned now2026-11-15 05:11 UTC13 files · 10.4 GB

Use it

$ fw get mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit
# manifest sha256 f46094ae874b… · 10.4 GB · 13 files
$ fw verify ./DeepSeek-V4-Pro-Qwen3.5-9B-8bit mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit.json --dir ./DeepSeek-V4-Pro-Qwen3.5-9B-8bit $ python3 fw.py verify ./DeepSeek-V4-Pro-Qwen3.5-9B-8bit ./mlx-community__DeepSeek-V4-Pro-Qwen3.5-9B-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit --revision 93b502eb9ef5256e2e7b00b3a5c0081803ffe10d --local-dir ./DeepSeek-V4-Pro-Qwen3.5-9B-8bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit", revision="93b502eb9ef5256e2e7b00b3a5c0081803ffe10d") model = AutoModelForImageTextToText.from_pretrained("mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit", revision="93b502eb9ef5256e2e7b00b3a5c0081803ffe10d", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit --revision 93b502eb9ef5256e2e7b00b3a5c0081803ffe10d
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
850f1005a5908c8224ba461784536287e578c84459c3fbbe1ded949806d585a2
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: DeepSeek-V4-Pro-Qwen3.5-9B-8bitDate: 2026-11-15Commit: 93b502eSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit
Pinned commit
93b502eb9ef5256e2e7b00b3a5c0081803ffe10d
Manifest
DeepSeek-V4-Pro-Qwen3.5-9B-8bit.json · .minisig
Manifest sha256
f46094ae874b331a38b19680f569593cb3524a8c6bb6367a262ca94adf61b5bc
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:11 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit.json.minisig $ minisign -Vm DeepSeek-V4-Pro-Qwen3.5-9B-8bit.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

Jackrong/DeepSeek-V4-Pro-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/DeepSeek-V4-Pro-Qwen3.5-9B-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-V4-Pro-Qwen3.5-9B-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-8bit

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