CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.minicpm / MiniCPM-V-4.7-35B-A3B-mxfp4
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.minicpmSubject:

MiniCPM-V-4.7-35B-A3B-mxfp4

Date: 2026-11-15Commit: 810419dSigned: 2DC28CC7B26A283B ✓

Image text to text model with 35.2B parameters. Safetensors weights, 22.5 GB in all. Published by mlx-community under Apache-2.0.

35.2B params22.5GBMiniCPM-V-4.7-35B-A3B-mxfp4safetensorspermissive
FactsParams35.2BSize22.5 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4
# manifest sha256 4c4373b43e84… · 22.5 GB · 17 files
$ fw verify ./MiniCPM-V-4.7-35B-A3B-mxfp4 mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4
From sourceHosted (signed)mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4Last check: 2026-11-15 05:05 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
22.5 GB
Weights
22.5 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 05:05 UTCpassed

Model card

From the publisher at commit 810419d. Shown as plain text with links; images open at the publisher.

MiniCPM-V-4.7-35B-A3B-mxfp4#

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.

MXFP4 weight quantization (mxfp4, group size 32). 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-mxfp4 --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-mxfp4 --dtype bfloat16 -q --q-bits 4 --q-group-size 32 --q-mode mxfp4

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 · 22.5 GBWeights 22.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.62 KB82a4f3aec9472b1305d9240e17ad75a4051a623e77d7af0ea5eae07d501201a0
chat_template.jinja7.25 KBc4531cacbf2a0ab65170433d7a4f371d11b7599cf96c04b192e6372432636c70
config.json23.9 KB28286971d65db429fa1908bcb84b31a171ea8cc470d0747fb7afb975e7f07d52
conversion.json9.55 KBb7b9bf803537f40db9f45cd478d8569ecdf11078ffa5032c3e218a4ba6338d71
generation_config.json186 B7fa47217744f0e0918f6cf846e7541e4f322e6bc66917044cf2ad580699216c8
model-00001-of-00005.safetensors5.30 GB6aebe2c7209199d2ec582b88ff0c169ef5825ea3edabdc509256c6fb52e5e44e
model-00002-of-00005.safetensors5.37 GB772a54a1539e2026f42e114b7fb3ea2d9fbd28d764f808c9564e2e55aa88997e
model-00003-of-00005.safetensors5.31 GB50c78b02540450c580f7dbe1938f3d58703e2b1601d85541a405a2d69e3d1ca0
model-00004-of-00005.safetensors5.25 GBd86d6636e2fa67c8af0cbc08cdcd706a4f2f440e06184ed622683b054233a418
model-00005-of-00005.safetensors1.29 GB92003f3d002afd3846574de26b8a3a3ede809e48d41dbcec45ffbd42ee692c22
model.safetensors.index.json168 KB00e341c8b5d019c885b33d21d66c44fbbd75a91c6da9271b87692ef394139b4b
preprocessor_config.json148 Bc64289d04f36e48d9d059e3a0069f54062b2ef6044a807adb448b98449cb54de
processor_config.json764 B8540e97ca17871b46aca8639b05f26db4eb4ac39d271b705c9cdbc3e32abbe07
tokenizer.json20.0 MBe4608c5d7b3f4f30ba83be16a82cdac856b2e7191d40f0a08cbacc76c2a926ee
tokenizer_config.json1.16 KBbe74f538ac586f2daac1ede56d421e915d196fba24171bc8fcd05256e42108bc
validation.json1.60 KB4d3589b23529e68d5e6903854800f21df4a945dc0670d227cead29d7840cc512
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
810419dd09 pinned now2026-11-15 05:05 UTC17 files · 22.5 GB

Use it

$ fw get mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4
# manifest sha256 4c4373b43e84… · 22.5 GB · 17 files
$ fw verify ./MiniCPM-V-4.7-35B-A3B-mxfp4 mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4
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-mxfp4.json --dir ./MiniCPM-V-4.7-35B-A3B-mxfp4 $ python3 fw.py verify ./MiniCPM-V-4.7-35B-A3B-mxfp4 ./mlx-community__MiniCPM-V-4.7-35B-A3B-mxfp4.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-mxfp4 --revision 810419dd09762d63aad6da5b6a418c4af8946e60 --local-dir ./MiniCPM-V-4.7-35B-A3B-mxfp4
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-mxfp4", revision="810419dd09762d63aad6da5b6a418c4af8946e60") model = AutoModelForImageTextToText.from_pretrained("mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4", revision="810419dd09762d63aad6da5b6a418c4af8946e60", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4 --revision 810419dd09762d63aad6da5b6a418c4af8946e60
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
82a4f3aec9472b1305d9240e17ad75a4051a623e77d7af0ea5eae07d501201a0
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-mxfp4Date: 2026-11-15Commit: 810419dSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4
Pinned commit
810419dd09762d63aad6da5b6a418c4af8946e60
Manifest
MiniCPM-V-4.7-35B-A3B-mxfp4.json · .minisig
Manifest sha256
4c4373b43e84a6cca0935cc58a2cf6f2079ffac54f33b38138905cea19af0c8d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:05 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-mxfp4.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4.json.minisig $ minisign -Vm MiniCPM-V-4.7-35B-A3B-mxfp4.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-mxfp4
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-mxfp4.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4

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