CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.minicpm / MiniCPM-V-4.7-35B-A3B-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.minicpmSubject:

MiniCPM-V-4.7-35B-A3B-8bit

Date: 2026-11-15Commit: f7d1667Signed: 2DC28CC7B26A283B ✓

Image text to text model with 35.2B parameters. Safetensors weights, 39.9 GB in all. Published by mlx-community under Apache-2.0.

35.2B params39.9GBMiniCPM-V-4.7-35B-A3B-8bitsafetensorspermissive
FactsParams35.2BSize39.9 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/MiniCPM-V-4.7-35B-A3B-8bit
# manifest sha256 6ce75e569741… · 39.9 GB · 20 files
$ fw verify ./MiniCPM-V-4.7-35B-A3B-8bit mlx-community/MiniCPM-V-4.7-35B-A3B-8bit
From sourceHosted (signed)mlx-community/MiniCPM-V-4.7-35B-A3B-8bitLast check: 2026-11-15 05:19 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
39.9 GB
Weights
39.8 GB (safetensors)
Parameters
35.2B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
20, 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 05:19 UTCpassed

Model card

From the publisher at commit f7d1667. Shown as plain text with links; images open at the publisher.

MiniCPM-V-4.7-35B-A3B-8bit#

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.

8BIT 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-8bit --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-8bit --dtype bfloat16 -q --q-bits 8 --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

20 files · 39.9 GBWeights 39.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 20 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.62 KB933b487741b233585536984972266c123e217875313f5b584f9e8ad5b0304697
chat_template.jinja7.25 KBc4531cacbf2a0ab65170433d7a4f371d11b7599cf96c04b192e6372432636c70
config.json23.9 KB54285f4676da330e173b1723db587383a5ee6554a79b3a45aa186fdc5a0b25d4
conversion.json10.00 KBd2a71146d0fcb9b21e7070cddf2b6f61c85f2829351ddc4fe73ad54c10701edd
generation_config.json186 B7fa47217744f0e0918f6cf846e7541e4f322e6bc66917044cf2ad580699216c8
model-00001-of-00008.safetensors5.23 GBb059ca75886e1a969992e2a5166b61b92a3546d23a782739004a26c89bb69072
model-00002-of-00008.safetensors5.24 GBb493b9214926d21d094fcb6bb89ca63523bc6f275c69679173f7e359dfe2a4b4
model-00003-of-00008.safetensors5.20 GB3b6e95b6613b14b0740123dfadfe3ea6b16fb7f66f4c7a989c38c8eaf5e769ac
model-00004-of-00008.safetensors5.17 GBdc3c9ad7cea7824c7f0df15c5451d7d700e598dfb55c18db2c3a699fdbd0fdf0
model-00005-of-00008.safetensors5.24 GBd90c5b209a5fd598d6dd475495cec57fc04b2afa8ff1fb60610a8fea55e155e0
model-00006-of-00008.safetensors5.20 GB38dbc979e6e31e55be8c540f334a49c18c920ffb8ec36fe025d6c8c5207b6762
model-00007-of-00008.safetensors5.17 GBfd2555d4b09ae6a38bf7b37a38f52458023faa562a205d6c0d0282d649891e2f
model-00008-of-00008.safetensors3.39 GBefe1def256e8c970b512e381e7a49d2c776ceaa6d409b4184cc89691fe3ea6d1
model.safetensors.index.json199 KBc42f42161d7a0fafa6711a68323675fb271921f234495f378ac590d9d4ad77c7
preprocessor_config.json148 Bc64289d04f36e48d9d059e3a0069f54062b2ef6044a807adb448b98449cb54de
processor_config.json764 B8540e97ca17871b46aca8639b05f26db4eb4ac39d271b705c9cdbc3e32abbe07
tokenizer.json20.0 MBe4608c5d7b3f4f30ba83be16a82cdac856b2e7191d40f0a08cbacc76c2a926ee
tokenizer_config.json1.16 KBbe74f538ac586f2daac1ede56d421e915d196fba24171bc8fcd05256e42108bc
validation.json1.58 KBa9d64cc49650ffd7841fed463d3bd5ed68f452001b2e2647e0cd096ba6c0cfff
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f7d166710f pinned now2026-11-15 05:19 UTC20 files · 39.9 GB

Use it

$ fw get mlx-community/MiniCPM-V-4.7-35B-A3B-8bit
# manifest sha256 6ce75e569741… · 39.9 GB · 20 files
$ fw verify ./MiniCPM-V-4.7-35B-A3B-8bit mlx-community/MiniCPM-V-4.7-35B-A3B-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/MiniCPM-V-4.7-35B-A3B-8bit.json --dir ./MiniCPM-V-4.7-35B-A3B-8bit $ python3 fw.py verify ./MiniCPM-V-4.7-35B-A3B-8bit ./mlx-community__MiniCPM-V-4.7-35B-A3B-8bit.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-8bit --revision f7d166710f377cff3981ecab850ba83d2aef07b7 --local-dir ./MiniCPM-V-4.7-35B-A3B-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/MiniCPM-V-4.7-35B-A3B-8bit", revision="f7d166710f377cff3981ecab850ba83d2aef07b7") model = AutoModelForImageTextToText.from_pretrained("mlx-community/MiniCPM-V-4.7-35B-A3B-8bit", revision="f7d166710f377cff3981ecab850ba83d2aef07b7", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/MiniCPM-V-4.7-35B-A3B-8bit --revision f7d166710f377cff3981ecab850ba83d2aef07b7
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
933b487741b233585536984972266c123e217875313f5b584f9e8ad5b0304697
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-8bitDate: 2026-11-15Commit: f7d1667Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/MiniCPM-V-4.7-35B-A3B-8bit
Pinned commit
f7d166710f377cff3981ecab850ba83d2aef07b7
Manifest
MiniCPM-V-4.7-35B-A3B-8bit.json · .minisig
Manifest sha256
6ce75e569741eb5dbb6067d821e99c3ad76ce65aefdc97429d47a684af188f5c
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:19 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-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/MiniCPM-V-4.7-35B-A3B-8bit.json.minisig $ minisign -Vm MiniCPM-V-4.7-35B-A3B-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

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-8bit
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-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/MiniCPM-V-4.7-35B-A3B-8bit

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