CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.minicpm / MiniCPM-V-4.7-35B-A3B-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.minicpmSubject:

MiniCPM-V-4.7-35B-A3B-4bit

Date: 2026-11-15Commit: 0e3b706Signed: 2DC28CC7B26A283B ✓

Image text to text model with 35.2B parameters. Safetensors weights, 23.5 GB in all. Published by mlx-community under Apache-2.0.

35.2B params23.5GBMiniCPM-V-4.7-35B-A3B-4bitsafetensorspermissive
FactsParams35.2BSize23.5 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/MiniCPM-V-4.7-35B-A3B-4bit
# manifest sha256 294ba0856e14… · 23.5 GB · 17 files
$ fw verify ./MiniCPM-V-4.7-35B-A3B-4bit mlx-community/MiniCPM-V-4.7-35B-A3B-4bit
From sourceHosted (signed)mlx-community/MiniCPM-V-4.7-35B-A3B-4bitLast check: 2026-11-15 05:13 UTC
Run at homeGet help

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

Quantized of MiniCPM-V-4.7-35B-A3B.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
23.5 GB
Weights
23.5 GB (safetensors)
Parameters
35.2B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
17, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.minicpm
Lineage

Original release from the publisher.

Base model: openbmb/MiniCPM-V-4.7-35B-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 05:13 UTCpassed

Model card

From the publisher at commit 0e3b706. Shown as plain text with links; images open at the publisher.

MiniCPM-V-4.7-35B-A3B-4bit#

Converted from openbmb/MiniCPM-V-4.7-35B-A3B at revision 17e651151c161dce119cd0ac57570f60da8a0b40 with MLX-VLM main (e928101a144a3f11a27c7ef8d71b6d889b2d250c, version 0.7.8). Support was added in PR #2499.

4BIT weight quantization (affine, group size 64). This is mixed precision: vision modules, visual mergers, embeddings, output heads, and linear attention remain BF16; recurrent A_log tensors retain their source precision. The 35B-A3B expert routers use 8-bit affine quantization.

See the original model card for the architecture, intended uses, and limitations. This conversion retains the source model's apache-2.0 license.

Usage#

Install MLX-VLM from main with MiniCPM-V 4.7 support:

pip install -U git+https://github.com/Blaizzy/mlx-vlm.git@main
mlx_vlm.generate --model mlx-community/MiniCPM-V-4.7-35B-A3B-4bit --image path/to/image.jpg --prompt "Describe this image." --max-tokens 200 --temperature 0

The native NumPy/Pillow processor requires neither PyTorch nor remote code. It supports text, images, multiple images, and video. The default visual downsampling is 16x; pass --processor-kwargs '{"downsample_mode": "4x"}' for finer detail.

Reproduce conversion#

mlx_vlm.convert --hf-path openbmb/MiniCPM-V-4.7-35B-A3B --revision 17e651151c161dce119cd0ac57570f60da8a0b40 --mlx-path MiniCPM-V-4.7-35B-A3B-4bit --dtype bfloat16 -q --q-bits 4 --q-group-size 64 --q-mode affine

For the exact converter version, install MLX-VLM at commit e928101a144a3f11a27c7ef8d71b6d889b2d250c. Conversion options, per-module quantization overrides, and weight SHA-256 hashes are recorded in conversion.json.

Validation#

The saved checkpoint passed strict reloading, quantization configuration checks, greedy text generation, and cat-image generation in both 16x and 4x downsampling modes on JarvisLabs RTX PRO 6000 Blackwell (cuda) with MLX 0.32.3. See validation.json for the outputs and environment. These are smoke checks, not a quality benchmark. Floating-point 4-bit formats can differ in output quality from affine quantization.

Files

17 files · 23.5 GBWeights 23.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.62 KBa6b6c5fb9a63f06407563f3dea3625e706eec4349dbaf2f070cd6508c86b2e45
chat_template.jinja7.25 KBc4531cacbf2a0ab65170433d7a4f371d11b7599cf96c04b192e6372432636c70
config.json23.9 KB61335970616d168207bbf4d02daf87da7fe051ade19540d8711a8b37c1a06921
conversion.json9.52 KBbdda5e1c92760e4192358c12ca10b94254d0a58d23af5db53356dbbb558c124a
generation_config.json186 B7fa47217744f0e0918f6cf846e7541e4f322e6bc66917044cf2ad580699216c8
model-00001-of-00005.safetensors5.31 GB84a6955049b3d7428220c7f82dfd18701a8b932e99c8f2fee78a5c496d954636
model-00002-of-00005.safetensors5.29 GB06ea042631cac78852e4283b12857c7b58f28dfa824d1cd6ba0bd9374701b5a4
model-00003-of-00005.safetensors5.36 GBaf2cca3162bc19f8de16cd3c76e169cb875a55b39786531d81fb55bc648035fe
model-00004-of-00005.safetensors5.35 GB1c90bac77652fd7720556e73cdc66658b3daa4be0f205d4b8d2fabe3580c89c0
model-00005-of-00005.safetensors2.21 GB4e774554cb00e35a0c1e043bae857e2e6f99efebb657a8279ec96aba1d441b52
model.safetensors.index.json199 KBa369a2f73e06421915f7f1f04633f1db64c7fda170e5f5f3d1bec865cd1a8652
preprocessor_config.json148 Bc64289d04f36e48d9d059e3a0069f54062b2ef6044a807adb448b98449cb54de
processor_config.json764 B8540e97ca17871b46aca8639b05f26db4eb4ac39d271b705c9cdbc3e32abbe07
tokenizer.json20.0 MBe4608c5d7b3f4f30ba83be16a82cdac856b2e7191d40f0a08cbacc76c2a926ee
tokenizer_config.json1.16 KBbe74f538ac586f2daac1ede56d421e915d196fba24171bc8fcd05256e42108bc
validation.json1.60 KBd34c639d4df2cef06831c96c564fedee6ab0b7a6bea6973287a30d026dce4462
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0e3b706c15 pinned now2026-11-15 05:13 UTC17 files · 23.5 GB

Use it

$ fw get mlx-community/MiniCPM-V-4.7-35B-A3B-4bit
# manifest sha256 294ba0856e14… · 23.5 GB · 17 files
$ fw verify ./MiniCPM-V-4.7-35B-A3B-4bit mlx-community/MiniCPM-V-4.7-35B-A3B-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/MiniCPM-V-4.7-35B-A3B-4bit.json --dir ./MiniCPM-V-4.7-35B-A3B-4bit $ python3 fw.py verify ./MiniCPM-V-4.7-35B-A3B-4bit ./mlx-community__MiniCPM-V-4.7-35B-A3B-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/MiniCPM-V-4.7-35B-A3B-4bit --revision 0e3b706c1599ad95294122c67c77ce662de18794 --local-dir ./MiniCPM-V-4.7-35B-A3B-4bit
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/MiniCPM-V-4.7-35B-A3B-4bit", revision="0e3b706c1599ad95294122c67c77ce662de18794") model = AutoModelForImageTextToText.from_pretrained("mlx-community/MiniCPM-V-4.7-35B-A3B-4bit", revision="0e3b706c1599ad95294122c67c77ce662de18794", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/MiniCPM-V-4.7-35B-A3B-4bit --revision 0e3b706c1599ad95294122c67c77ce662de18794
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
a6b6c5fb9a63f06407563f3dea3625e706eec4349dbaf2f070cd6508c86b2e45
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.minicpmSubject: MiniCPM-V-4.7-35B-A3B-4bitDate: 2026-11-15Commit: 0e3b706Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/MiniCPM-V-4.7-35B-A3B-4bit
Pinned commit
0e3b706c1599ad95294122c67c77ce662de18794
Manifest
MiniCPM-V-4.7-35B-A3B-4bit.json · .minisig
Manifest sha256
294ba0856e14a30511a25256683884394c9d4914cae5e8283f5b0ead850020c1
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:13 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/MiniCPM-V-4.7-35B-A3B-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/MiniCPM-V-4.7-35B-A3B-4bit.json.minisig $ minisign -Vm MiniCPM-V-4.7-35B-A3B-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

openbmb/MiniCPM-V-4.7-35B-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/MiniCPM-V-4.7-35B-A3B-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. MiniCPM-V-4.7-35B-A3B-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/MiniCPM-V-4.7-35B-A3B-4bit

Related models

All of alt.freeweights.minicpm →
From: openbmb <huggingface.co/openbmb>Subject: AgentCPM-Explore-GGUF
From: openbmb <huggingface.co/openbmb>Subject: AgentCPM-Report
From: openbmb <huggingface.co/openbmb>Subject: AgentCPM-Report-GGUF
From: openbmb <huggingface.co/openbmb>Subject: BitCPM-CANN-0.5B-gguf
From: openbmb <huggingface.co/openbmb>Subject: BitCPM-CANN-1B-gguf
From: openbmb <huggingface.co/openbmb>Subject: BitCPM-CANN-3B-gguf